Manufact

LeaderboardBack to leaderboard

AgentProof

isagentproof.com/mcp

View checks

Protocol: MCP 2025-11-25
Server version: 1.0.0
Website: isagentproof.com
Supports: Tools

Overall score

How is this score calculated?

Last reviewed at Nov 11, 2026, 15:52:24 UTC

Server metadata

Warnings80/100

Identity, discovery, and usage metadata advertised during the MCP handshake.

Stable server name

agentproof

10/10Source

Human-readable title

AgentProof

10/10Source

Useful description

Describe what the server helps an agent do.

0/20Source

Server version

Version 1.0.0

10/10Source

Public website

Website: isagentproof.com

10/10Source

Scalable or high-resolution icon

1 icon advertised, including a scalable or high-resolution asset.

10/10Source

Server instructions

Usage instructions provided for agents.

20/20Source

Declared capabilities

Supports Tools.

10/10Source

Server instructions

AgentProof tools. Tools act on the account's single workspace; get_account returns that workspace and the user's role. Only owners and admins can manage members. start_audit tests a live website the user owns or may test; start_run starts any agent task. Each agent run uses one credit; get_billing shows the credits left. Payment, ownership transfer and deletion happen on the AgentProof website.

Discoverability

33/100

Client listings and public setup information.

mcp.json or server-card.json

Either mcp.json or an MCP Server Card declaring this endpoint passes.

The manifest declares this MCP server's exact endpoint.

FoundSource

Setup instructions at MCP URL

The MCP endpoint publishes connection instructions for this server.

FoundSource

ChatGPT

No ChatGPT listing has been confirmed yet.

UnverifiedHow to get listed

Claude

No Claude listing has been confirmed yet.

UnverifiedHow to get listed

CursorGrok BotGrok

No Cursor marketplace listing has been confirmed yet.

UnverifiedHow to get listed

Muse

No Muse listing has been confirmed yet.

UnverifiedHow to get listed

4 unverified checks. Unverified checks earn no points until confirmed.

Protocol

Pass100/100

Connection, authentication, and protocol compatibility.

MCP negotiation succeeds (v1/v2)

MCP legacy negotiation succeeded in 1851ms

Source

Tools list returns results

20 tool(s) returned

Source

Resources list responds

0 resource(s) returned

Source

Server declares tools capability

Server declares tools capability in initialize response

Source

Tools

Pass100/100

Tool definitions, annotations, and client compatibility.

All tools have descriptions

All tools have non-empty descriptions

All tools have OpenAI behavior hints

All tools declare the three OpenAI behavior hints as booleans

Source

Claude Code metadata fits its 2 KB fields

Tool descriptions and server instructions fit Claude Code's 2 KB fields

Source

Skills over MCP resources are readable

Server does not advertise the Skills over MCP extension

Tool names follow the MCP 1–128 character range

All tool names follow the MCP recommended length

Source

Tool input schemas have a valid object structure

All tool input schemas have a valid object structure

Source

Claude tool names are within 64 characters

All tool names are within Claude's 64-character limit

Source

Claude tools declare applicable behavior hints

All tools include an applicable readOnlyHint or destructiveHint

Source

Cursor tool-name budget advisory

No tool name independently exhausts Cursor's observed 60-character combined budget

Observed behavior

Tool names use valid characters

All tool names use valid characters

Source

All tools have a display title

Source

ChatGPT tool names are unique

All tool names are unique

Source

Tool names follow MCP uniqueness guidance

All tool names are unique

Source

Tool input header annotations are valid

All x-mcp-header annotations satisfy Streamable HTTP requirements

Source

OpenAI file parameters use valid schemas

All declared OpenAI file parameters use reviewer-valid schemas

Source

Tool text has no hidden control characters

No invisible or control characters found in tool-facing text

Source

Declared output schemas have a valid basic structure

0 declared output schema(s) pass basic structural validation; schemas may describe any JSON value, including arrays

Source

MCP Apps

Not applicableOptional

App resources, metadata, and rendering requirements.

View resources declare a domain

No view resources found — view checks skipped

Source

View resource envelope is valid

No view resources found — view checks skipped

Tool-linked resource URI is readable

No view resources found — view checks skipped

Source

All discovered view resources were inspected

No view resources found — view checks skipped

Source

Views do not request nested iframe domains

No view resources found — view checks skipped

Source

View resource metadata complete

No view resources found — view checks skipped

Source

Tool invocation metadata present

No view resources found — view checks skipped

Source

CSP metadata covers literal external origins

No view resources found — view checks skipped

Source

Tool visibility metadata is valid

No view resources found — view checks skipped

Source

Declared domains respond

No view resources found — view checks skipped

Tool documentation quality

80/100

How clearly each tool’s title, description, input and output schemas, and behavior annotations guide an agent.

get_accountTitles 99Descriptions 90Inputs 100Annotations 100Outputs 087/100

get_account

Title99/100

Get account

The title clearly communicates the tool’s action and subject. Keep it concise.

Description90/100

Returns the signed-in AgentProof account (ID, email, name, email verification) and its single workspace and role.

The description explains the capability, when to use it, and what to expect.

Inputs100/100

This tool declares no inputs, so argument descriptions are not needed.

No input fields.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Get account",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "get_account",
  "title": "Get account",
  "description": "Returns the signed-in AgentProof account (ID, email, name, email verification) and its single workspace and role.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  },
  "annotations": {
    "title": "Get account",
    "readOnlyHint": true,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": false
  }
}

get_billingTitles 99Descriptions 90Inputs 100Annotations 100Outputs 087/100

get_billing

Title99/100

Get billing status

The title clearly communicates the tool’s action and subject. Keep it concise.

Description90/100

Returns a workspace's subscription status, plan name, renewal or end date, and credits left this month. One credit pays for one agent run.

The description explains the capability, when to use it, and what to expect.

Inputs100/100

This tool declares no inputs, so argument descriptions are not needed.

No input fields.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Get billing status",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "get_billing",
  "title": "Get billing status",
  "description": "Returns a workspace's subscription status, plan name, renewal or end date, and credits left this month. One credit pays for one agent run.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  },
  "annotations": {
    "title": "Get billing status",
    "readOnlyHint": true,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": false
  }
}

create_workspaceTitles 100Descriptions 88Inputs 75Annotations 100Outputs 080/100

create_workspace

Title100/100

Create workspace

The title clearly communicates the tool’s action and subject. Keep it concise.

Description88/100

Creates a workspace owned by the signed-in user and makes it current. Only accounts without a workspace can create one.

The description explains the capability, when to use it, and what to expect.

Inputs75/100

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

name

Workspace name, 1 to 60 characters.

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Create workspace",
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "create_workspace",
  "title": "Create workspace",
  "description": "Creates a workspace owned by the signed-in user and makes it current. Only accounts without a workspace can create one.",
  "inputSchema": {
    "type": "object",
    "required": [
      "name"
    ],
    "properties": {
      "name": {
        "type": "string",
        "maxLength": 60,
        "description": "Workspace name, 1 to 60 characters."
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "title": "Create workspace",
    "readOnlyHint": false,
    "openWorldHint": false,
    "idempotentHint": false,
    "destructiveHint": false
  }
}

rename_workspaceTitles 100Descriptions 67Inputs 75Annotations 100Outputs 075/100

rename_workspace

Title100/100

Rename workspace

The title clearly communicates the tool’s action and subject. Keep it concise.

Description67/100

Renames a workspace. Owner only.

Explain mutations, irreversible effects, or prerequisites that matter before calling this tool.

Inputs75/100

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

name

New name, 1 to 60 characters.

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Rename workspace",
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": true
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "rename_workspace",
  "title": "Rename workspace",
  "description": "Renames a workspace. Owner only.",
  "inputSchema": {
    "type": "object",
    "required": [
      "name"
    ],
    "properties": {
      "name": {
        "type": "string",
        "maxLength": 60,
        "description": "New name, 1 to 60 characters."
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "title": "Rename workspace",
    "readOnlyHint": false,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": true
  }
}

list_membersTitles 100Descriptions 75Inputs 100Annotations 100Outputs 083/100

list_members

Title100/100

List members

The title clearly communicates the tool’s action and subject. Keep it concise.

Description75/100

Lists a workspace's members and roles. Owners and admins also get the pending invitations.

Describe the returned information so the agent knows whether it will answer the request.

Inputs100/100

This tool declares no inputs, so argument descriptions are not needed.

No input fields.

Annotations100/100

All four behavior hints are declared.

{
  "title": "List members",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "list_members",
  "title": "List members",
  "description": "Lists a workspace's members and roles. Owners and admins also get the pending invitations.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  },
  "annotations": {
    "title": "List members",
    "readOnlyHint": true,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": false
  }
}

invite_memberTitles 100Descriptions 88Inputs 75Annotations 100Outputs 080/100

invite_member

Title100/100

Invite member

The title clearly communicates the tool’s action and subject. Keep it concise.

Description88/100

Emails an invitation to join a workspace. The invitation expires in 7 days. Admins invite members; only the owner can invite admins.

The description explains the capability, when to use it, and what to expect.

Inputs75/100

Explain the meaning of this value, not just its name.

Email address to invite.

Clear enough to supply this argument.

role

Role after joining.

Explain the meaning of this value, not just its name.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Invite member",
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "invite_member",
  "title": "Invite member",
  "description": "Emails an invitation to join a workspace. The invitation expires in 7 days. Admins invite members; only the owner can invite admins.",
  "inputSchema": {
    "type": "object",
    "required": [
      "email"
    ],
    "properties": {
      "role": {
        "enum": [
          "member",
          "admin"
        ],
        "type": "string",
        "default": "member",
        "description": "Role after joining."
      },
      "email": {
        "type": "string",
        "format": "email",
        "description": "Email address to invite."
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "title": "Invite member",
    "readOnlyHint": false,
    "openWorldHint": true,
    "idempotentHint": false,
    "destructiveHint": false
  }
}

revoke_invitationTitles 99Descriptions 75Inputs 91Annotations 100Outputs 081/100

revoke_invitation

Title99/100

Revoke invitation

The title clearly communicates the tool’s action and subject. Keep it concise.

Description75/100

Cancels a pending invitation. Owners and admins only.

Explain mutations, irreversible effects, or prerequisites that matter before calling this tool.

Inputs91/100

Input documentation gives an agent enough context to populate the arguments.

invitation_id

Invitation ID from list_members.

Clear enough to supply this argument.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Revoke invitation",
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": true
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "revoke_invitation",
  "title": "Revoke invitation",
  "description": "Cancels a pending invitation. Owners and admins only.",
  "inputSchema": {
    "type": "object",
    "required": [
      "invitation_id"
    ],
    "properties": {
      "invitation_id": {
        "type": "string",
        "description": "Invitation ID from list_members."
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "title": "Revoke invitation",
    "readOnlyHint": false,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": true
  }
}

change_member_roleTitles 100Descriptions 69Inputs 75Annotations 100Outputs 075/100

change_member_role

Title100/100

Change member role

The title clearly communicates the tool’s action and subject. Keep it concise.

Description69/100

Makes a member an admin or a member. Owner only; ownership itself moves only from the dashboard.

Explain mutations, irreversible effects, or prerequisites that matter before calling this tool.

Inputs75/100

Explain the meaning of this value, not just its name.

role

New role.

Explain the meaning of this value, not just its name.

user_id

Member user ID from list_members.

Clear enough to supply this argument.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Change member role",
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": true
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "change_member_role",
  "title": "Change member role",
  "description": "Makes a member an admin or a member. Owner only; ownership itself moves only from the dashboard.",
  "inputSchema": {
    "type": "object",
    "required": [
      "user_id",
      "role"
    ],
    "properties": {
      "role": {
        "enum": [
          "member",
          "admin"
        ],
        "type": "string",
        "description": "New role."
      },
      "user_id": {
        "type": "string",
        "description": "Member user ID from list_members."
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "title": "Change member role",
    "readOnlyHint": false,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": true
  }
}

remove_memberTitles 99Descriptions 91Inputs 91Annotations 100Outputs 085/100

remove_member

Title99/100

Remove member

The title clearly communicates the tool’s action and subject. Keep it concise.

Description91/100

Removes a person from a workspace. Their past runs and reports stay with the workspace. Admins remove members; only the owner removes admins.

The description explains the capability, when to use it, and what to expect.

Inputs91/100

Input documentation gives an agent enough context to populate the arguments.

user_id

Member user ID from list_members.

Clear enough to supply this argument.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Remove member",
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": true
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "remove_member",
  "title": "Remove member",
  "description": "Removes a person from a workspace. Their past runs and reports stay with the workspace. Admins remove members; only the owner removes admins.",
  "inputSchema": {
    "type": "object",
    "required": [
      "user_id"
    ],
    "properties": {
      "user_id": {
        "type": "string",
        "description": "Member user ID from list_members."
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "title": "Remove member",
    "readOnlyHint": false,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": true
  }
}

leave_workspaceTitles 100Descriptions 73Inputs 100Annotations 100Outputs 083/100

leave_workspace

Title100/100

Leave workspace

The title clearly communicates the tool’s action and subject. Keep it concise.

Description73/100

Removes the signed-in user from a workspace they do not own.

Explain mutations, irreversible effects, or prerequisites that matter before calling this tool.

Inputs100/100

This tool declares no inputs, so argument descriptions are not needed.

No input fields.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Leave workspace",
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": false,
  "destructiveHint": true
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "leave_workspace",
  "title": "Leave workspace",
  "description": "Removes the signed-in user from a workspace they do not own.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  },
  "annotations": {
    "title": "Leave workspace",
    "readOnlyHint": false,
    "openWorldHint": false,
    "idempotentHint": false,
    "destructiveHint": true
  }
}

list_agentsTitles 99Descriptions 82Inputs 100Annotations 100Outputs 085/100

list_agents

Title99/100

List agents

The title clearly communicates the tool’s action and subject. Keep it concise.

Description82/100

Lists the workspace's two agents, the Attack Agent and the Defense Agent, and whether each one is running.

Describe the returned information so the agent knows whether it will answer the request.

Inputs100/100

This tool declares no inputs, so argument descriptions are not needed.

No input fields.

Annotations100/100

All four behavior hints are declared.

{
  "title": "List agents",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "list_agents",
  "title": "List agents",
  "description": "Lists the workspace's two agents, the Attack Agent and the Defense Agent, and whether each one is running.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  },
  "annotations": {
    "title": "List agents",
    "readOnlyHint": true,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": false
  }
}

start_auditTitles 97Descriptions 87Inputs 94Annotations 100Outputs 084/100

start_audit

Title97/100

Start website audit

The title clearly communicates the tool’s action and subject. Keep it concise.

Description87/100

Starts an Attack Agent test of a live website with AgentProof's built-in safety rules: no real orders, no data changes, no heavy traffic. Uses one credit. If a confirmed finding matches a connected GitHub repository, a Defense Agent prepares a fix pull request and a retest follows, each using one more credit. Only for websites the user owns or has written permission to test.

The description explains the capability, when to use it, and what to expect.

Inputs94/100

Input documentation gives an agent enough context to populate the arguments.

confirm_permission

True only if the user confirmed they own the website or have written permission to test it.

Clear enough to supply this argument.

target

Website address to test, such as https://example.com.

Clear enough to supply this argument.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Start website audit",
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "start_audit",
  "title": "Start website audit",
  "description": "Starts an Attack Agent test of a live website with AgentProof's built-in safety rules: no real orders, no data changes, no heavy traffic. Uses one credit. If a confirmed finding matches a connected GitHub repository, a Defense Agent prepares a fix pull request and a retest follows, each using one more credit. Only for websites the user owns or has written permission to test.",
  "inputSchema": {
    "type": "object",
    "required": [
      "target",
      "confirm_permission"
    ],
    "properties": {
      "target": {
        "type": "string",
        "maxLength": 2048,
        "description": "Website address to test, such as https://example.com."
      },
      "confirm_permission": {
        "type": "boolean",
        "description": "True only if the user confirmed they own the website or have written permission to test it."
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "title": "Start website audit",
    "readOnlyHint": false,
    "openWorldHint": true,
    "idempotentHint": false,
    "destructiveHint": false
  }
}

start_runTitles 93Descriptions 74Inputs 80Annotations 100Outputs 076/100

start_run

Title93/100

Start agent run

The title clearly communicates the tool’s action and subject. Keep it concise.

Description74/100

Starts a task on the workspace's Attack Agent or Defense Agent with the given instructions. Choose the agent with team or agent_id. Uses one credit.

Describe the returned information so the agent knows whether it will answer the request.

Inputs80/100

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

agent_id

ID of the Attack Agent or Defense Agent from list_agents. Use this or team.

Clear enough to supply this argument.

prompt

Instructions for the agent.

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

target

Optional website address the run tests.

Explain what happens when this optional value is omitted.

team

Which agent runs the task. Use this or agent_id.

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Start agent run",
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "start_run",
  "title": "Start agent run",
  "description": "Starts a task on the workspace's Attack Agent or Defense Agent with the given instructions. Choose the agent with team or agent_id. Uses one credit.",
  "inputSchema": {
    "type": "object",
    "required": [
      "prompt"
    ],
    "properties": {
      "team": {
        "enum": [
          "attack",
          "defense"
        ],
        "type": "string",
        "description": "Which agent runs the task. Use this or agent_id."
      },
      "prompt": {
        "type": "string",
        "maxLength": 20000,
        "description": "Instructions for the agent."
      },
      "target": {
        "type": "string",
        "maxLength": 2048,
        "description": "Optional website address the run tests."
      },
      "agent_id": {
        "type": "string",
        "description": "ID of the Attack Agent or Defense Agent from list_agents. Use this or team."
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "title": "Start agent run",
    "readOnlyHint": false,
    "openWorldHint": true,
    "idempotentHint": false,
    "destructiveHint": false
  }
}

get_runTitles 99Descriptions 81Inputs 96Annotations 100Outputs 084/100

get_run

Title99/100

Get run

The title clearly communicates the tool’s action and subject. Keep it concise.

Description81/100

Returns a run's status, agent, target, times and report state, with its page on the AgentProof website.

The description explains the capability, when to use it, and what to expect.

Inputs96/100

Input documentation gives an agent enough context to populate the arguments.

run_id

Run ID from start_audit, start_run or list_reports.

Clear enough to supply this argument.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Get run",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "get_run",
  "title": "Get run",
  "description": "Returns a run's status, agent, target, times and report state, with its page on the AgentProof website.",
  "inputSchema": {
    "type": "object",
    "required": [
      "run_id"
    ],
    "properties": {
      "run_id": {
        "type": "string",
        "description": "Run ID from start_audit, start_run or list_reports."
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "title": "Get run",
    "readOnlyHint": true,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": false
  }
}

list_reportsTitles 99Descriptions 77Inputs 50Annotations 100Outputs 070/100

list_reports

Title99/100

List reports

The title clearly communicates the tool’s action and subject. Keep it concise.

Description77/100

Lists finished runs that have reports, newest first.

The description explains the capability, when to use it, and what to expect.

Inputs50/100

2 of 3 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.

agent_id

Only this agent's reports.

Clarify units, where to obtain this value, or conventions not already expressed in the schema.

cursor

nextCursor from the previous page.

Clear enough to supply this argument.

limit

Not provided

Missing description. Explain what this value means and how to supply it.

Annotations100/100

All four behavior hints are declared.

{
  "title": "List reports",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "list_reports",
  "title": "List reports",
  "description": "Lists finished runs that have reports, newest first.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "limit": {
        "type": "integer",
        "default": 20,
        "maximum": 50,
        "minimum": 1
      },
      "cursor": {
        "type": "string",
        "description": "nextCursor from the previous page."
      },
      "agent_id": {
        "type": "string",
        "description": "Only this agent's reports."
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "title": "List reports",
    "readOnlyHint": true,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": false
  }
}

list_findingsTitles 100Descriptions 83Inputs 84Annotations 100Outputs 081/100

list_findings

Title100/100

List findings

The title clearly communicates the tool’s action and subject. Keep it concise.

Description83/100

Lists security findings with title, severity, status and address, plus the fix pull request state for a run. Evidence stays on the run page.

The description explains the capability, when to use it, and what to expect.

Inputs84/100

Input documentation gives an agent enough context to populate the arguments.

run_id

Only findings from this run. Omit for the workspace's newest findings.

Clear enough to supply this argument.

Annotations100/100

All four behavior hints are declared.

{
  "title": "List findings",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "list_findings",
  "title": "List findings",
  "description": "Lists security findings with title, severity, status and address, plus the fix pull request state for a run. Evidence stays on the run page.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "run_id": {
        "type": "string",
        "description": "Only findings from this run. Omit for the workspace's newest findings."
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "title": "List findings",
    "readOnlyHint": true,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": false
  }
}

list_planned_runsTitles 100Descriptions 91Inputs 0Annotations 100Outputs 061/100

list_planned_runs

Title100/100

List planned runs

The title clearly communicates the tool’s action and subject. Keep it concise.

Description91/100

Lists the workspace's planned runs (not yet started) in time order, with team, website, start time and a calendar link, plus how many more runs can be planned this month and whether Auto schedule every month is on.

The description explains the capability, when to use it, and what to expect.

Inputs0/100

0 of 1 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.

limit

Not provided

Missing description. Explain what this value means and how to supply it.

Annotations100/100

All four behavior hints are declared.

{
  "title": "List planned runs",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "list_planned_runs",
  "title": "List planned runs",
  "description": "Lists the workspace's planned runs (not yet started) in time order, with team, website, start time and a calendar link, plus how many more runs can be planned this month and whether Auto schedule every month is on.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "limit": {
        "type": "integer",
        "default": 50,
        "maximum": 100,
        "minimum": 1
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "title": "List planned runs",
    "readOnlyHint": true,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": false
  }
}

set_monthly_auto_scheduleTitles 89Descriptions 87Inputs 86Annotations 100Outputs 080/100

set_monthly_auto_schedule

Title89/100

Set monthly Auto schedule

The title clearly communicates the tool’s action and subject. Keep it concise.

Description87/100

Turns Auto schedule every month on or off for the workspace. When on, AgentProof plans the rest of each credit month as Attack and Defense runs on the workspace's website. Turning it off keeps runs that are already planned.

Explain mutations, irreversible effects, or prerequisites that matter before calling this tool.

Inputs86/100

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

confirm_permission

True only if the user confirmed they own the website or have written permission to test it.

Clear enough to supply this argument.

enabled

True turns Auto schedule every month on, false turns it off.

Clear enough to supply this argument.

website

Optional website address for the schedule. Used only with confirm_permission and a verified domain.

Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Set monthly Auto schedule",
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "set_monthly_auto_schedule",
  "title": "Set monthly Auto schedule",
  "description": "Turns Auto schedule every month on or off for the workspace. When on, AgentProof plans the rest of each credit month as Attack and Defense runs on the workspace's website. Turning it off keeps runs that are already planned.",
  "inputSchema": {
    "type": "object",
    "required": [
      "enabled"
    ],
    "properties": {
      "enabled": {
        "type": "boolean",
        "description": "True turns Auto schedule every month on, false turns it off."
      },
      "website": {
        "type": "string",
        "maxLength": 2048,
        "description": "Optional website address for the schedule. Used only with confirm_permission and a verified domain."
      },
      "confirm_permission": {
        "type": "boolean",
        "description": "True only if the user confirmed they own the website or have written permission to test it."
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "title": "Set monthly Auto schedule",
    "readOnlyHint": false,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": false
  }
}

list_notification_destinationsTitles 100Descriptions 75Inputs 100Annotations 100Outputs 083/100

list_notification_destinations

Title100/100

List notification destinations

The title clearly communicates the tool’s action and subject. Keep it concise.

Description75/100

Lists where a workspace sends notifications (webhooks, Slack, Discord), with the events each one receives. Destinations are added on the AgentProof website.

Describe the returned information so the agent knows whether it will answer the request.

Inputs100/100

This tool declares no inputs, so argument descriptions are not needed.

No input fields.

Annotations100/100

All four behavior hints are declared.

{
  "title": "List notification destinations",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "list_notification_destinations",
  "title": "List notification destinations",
  "description": "Lists where a workspace sends notifications (webhooks, Slack, Discord), with the events each one receives. Destinations are added on the AgentProof website.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  },
  "annotations": {
    "title": "List notification destinations",
    "readOnlyHint": true,
    "openWorldHint": false,
    "idempotentHint": true,
    "destructiveHint": false
  }
}

send_test_notificationTitles 99Descriptions 87Inputs 91Annotations 100Outputs 084/100

send_test_notification

Title99/100

Send test notification

The title clearly communicates the tool’s action and subject. Keep it concise.

Description87/100

Sends a test notification to one destination and returns whether it was delivered. Owners and admins only.

Describe the returned information so the agent knows whether it will answer the request.

Inputs91/100

Input documentation gives an agent enough context to populate the arguments.

destination_id

Destination ID from list_notification_destinations.

Clear enough to supply this argument.

Annotations100/100

All four behavior hints are declared.

{
  "title": "Send test notification",
  "readOnlyHint": false,
  "openWorldHint": true,
  "idempotentHint": false,
  "destructiveHint": false
}

Output schema0/100

No output schema is declared. Add one for structured results so clients can interpret returned fields.

Not declared

Original tool metadata

{
  "name": "send_test_notification",
  "title": "Send test notification",
  "description": "Sends a test notification to one destination and returns whether it was delivered. Owners and admins only.",
  "inputSchema": {
    "type": "object",
    "required": [
      "destination_id"
    ],
    "properties": {
      "destination_id": {
        "type": "string",
        "description": "Destination ID from list_notification_destinations."
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "title": "Send test notification",
    "readOnlyHint": false,
    "openWorldHint": true,
    "idempotentHint": false,
    "destructiveHint": false
  }
}

Put your MCP to the test

A few tasks worth trying with this server, chosen from its reviewed tools. These have not been run.

01Get accountReturns the signed-in AgentProof account (ID, email, name, email verification) and its single workspace and role.
02List planned runsLists the workspace's planned runs (not yet started) in time order, with team, website, start time and a calendar link, plus how many more runs can be planne…
03List findingsLists security findings with title, severity, status and address, plus the fix pull request state for a run.
04Get billing statusReturns a workspace's subscription status, plan name, renewal or end date, and credits left this month.
05List agentsLists the workspace's two agents, the Attack Agent and the Defense Agent, and whether each one is running.

Want to run these tasks against your MCP server with us?

Test your MCP in Cloud Book a test call

Overview

Category: Developer tools

FAQ

AgentProof setup, tools, quality score, publishing readiness, and alternatives.

How do I add AgentProof to Claude, ChatGPT, or Cursor?

Add AgentProof to Claude, ChatGPT, or Cursor by connecting its remote MCP URL in each client's MCP settings. In Claude, add a custom connector. In ChatGPT, add an MCP app. In Cursor, add an MCP server under Settings. The MCP URL is https://isagentproof.com/mcp.

Is AgentProof MCP ready for ChatGPT and Claude?

As of November 11, 2026, AgentProof scores 100/100 on Manufact's MCP publishing checklist. The scan meets ChatGPT publishing checks and meets Claude publishing checks. Passing these checks does not guarantee marketplace approval.

How clear is AgentProof's MCP tool documentation?

As of November 11, 2026, AgentProof scores 80/100 in Manufact's review of tool titles, descriptions, input and output schemas, and behavior annotations. The review covers 20 of 20 discovered tools. The quality score measures documentation clarity; runtime behavior and marketplace readiness require separate checks.

What are the best alternatives to AgentProof?

As of November 12, 2026, alternatives to AgentProof in developer-tools on the Manufact MCP leaderboard include Speko, Manufact, AgentMail, Context, and Speko.

How can AgentProof improve its MCP documentation?

list_planned_runs is the lowest-scoring reviewed tool at 61/100. 0 of 1 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values. Open its review for feedback and a copyable fix prompt, then rerun the documentation review after updating your tool metadata.

Not your MCP?

Review any public or OAuth MCP server for protocol compatibility, tool documentation, and ChatGPT and Claude publishing readiness. No account required.

Get your MCP score

LeaderboardBack to leaderboardLeaderboardBack to leaderboard

Opening report…

Loading report overview

Server metadata

Loading server metadata

Discoverability

Loading discoverability

Protocol

Loading protocol

Tools

Loading tools

MCP Apps

Loading mcp apps

Tool documentation quality

Loading tool documentation quality

Manufact

Server metadata

Discoverability

Protocol

Tools

MCP Apps

Tool docsTool documentation quality

Title99/100

Description90/100

Inputs100/100

Annotations100/100

Output schema0/100

Title99/100

Description90/100

Inputs100/100

Annotations100/100

Output schema0/100

Title100/100

Description88/100

Inputs75/100

Annotations100/100

Output schema0/100

Title100/100

Description67/100

Inputs75/100

Annotations100/100

Output schema0/100

Title100/100

Description75/100

Inputs100/100

Annotations100/100

Output schema0/100

Title100/100

Description88/100

Inputs75/100

Annotations100/100

Output schema0/100

Title99/100

Description75/100

Inputs91/100

Annotations100/100

Output schema0/100

Title100/100

Description69/100

Inputs75/100

Annotations100/100

Output schema0/100

Title99/100

Description91/100

Inputs91/100

Annotations100/100

Output schema0/100

Title100/100

Description73/100

Inputs100/100

Annotations100/100

Output schema0/100

Title99/100

Description82/100

Inputs100/100

Annotations100/100

Output schema0/100

Title97/100

Description87/100

Inputs94/100

Annotations100/100

Output schema0/100

Title93/100

Description74/100

Inputs80/100

Annotations100/100

Output schema0/100

Title99/100

Description81/100

Inputs96/100

Annotations100/100

Output schema0/100

Title99/100

Description77/100

Inputs50/100

Tool documentation quality

Tool documentation quality