Use audit_server, propose_patch, verify_patch and get_verification_result to evaluate a metadata-only candidate. Apply source edits only after an Improved verdict, then redeploy and call confirm_patch. preview_run replays the recorded fallback; ping checks hosting.
Protocol
Pass100/10016 / 16 pts
Connection, authentication, and protocol compatibility.
How to fix: For tools that render a UI resource, add openai/toolInvocation with string fields invoking and invoked (present-tense labels shown while the tool runs and after it finishes, e.g. "Searching…" / "Searched").
How to fix: Use a ui:// URI and text/html;profile=mcp-app. For mcp-use v1, use widgetMetadata.metadata.widgetDescription; for v2, use the bound tool's view.description. The current description check reads _meta.ui.widgetDescription or _meta["openai/widgetDescription"] on resource contents or linked tools, not resource.description. Consequently, v2 view.description alone may leave this warning: report the checker compatibility gap instead of adding unsupported v1 fields or claiming the warning is fixed.
How to fix: For ChatGPT submission, set one exact HTTPS origin such as "https://app.example.com" on every view via _meta.ui.domain (or openai/widgetDomain). Paths are not valid and all views in one app must share the origin.
Expand internal abbreviations and remove technical prefixes from the display title.
Description88/100
Use to preview AX Lint's read-only verification viewer using the recorded live Railway run. Replays the completed S8 milestone and its recorded confirmation gates; does not run verification or apply a patch.
The description explains the capability, when to use it, and what to expect.
Inputs92/100
Input documentation gives an agent enough context to populate the arguments.
phase
Choose the complete recorded live run or an illustrative partial playback snapshot
The title clearly communicates the tool’s action and subject. Keep it concise.
Description85/100
Use to read live MCP tools/list and deployment identity, report deterministic metadata findings and provider-counted static tool tokens. Never executes target tools.
The description explains the capability, when to use it, and what to expect.
Inputs98/100
Input documentation gives an agent enough context to populate the arguments.
server_url
HTTP(S) MCP endpoint to inspect; only initialize and tools/list are called.
The title clearly communicates the tool’s action and subject. Keep it concise.
Description72/100
Use to propose validated description-only metadata improvements and deterministic source edits without writing files. Include every file defining accepted values or defaults, including validation constants, enums and handlers. Start with the highest-severity findings. Omit unknown facts from descriptions; return missing source facts as warnings. Requires a fresh audit.
The description explains the capability, when to use it, and what to expect.
Inputs8/100
2 of 23 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.
audit › audit_id
Not provided
Missing description. Explain what this value means and how to supply it.
audit › server_url
Not provided
Missing description. Explain what this value means and how to supply it.
audit › server_version
Not provided
Missing description. Explain what this value means and how to supply it.
audit › tools_hash
Not provided
Missing description. Explain what this value means and how to supply it.
audit › static_tool_tokens
Not provided
Missing description. Explain what this value means and how to supply it.
audit › tools › items › name
Not provided
Missing description. Explain what this value means and how to supply it.
audit › tools › items › description_chars
Not provided
Missing description. Explain what this value means and how to supply it.
audit › tools › items › params › items › name
Not provided
Missing description. Explain what this value means and how to supply it.
audit › tools › items › params › items › type
Not provided
Missing description. Explain what this value means and how to supply it.
audit › tools › items › params › items › required
Not provided
Missing description. Explain what this value means and how to supply it.
Name the specific action and subject instead of using a generic label such as ‘manage’ or ‘tool’.
Description94/100
Use to start single-turn baseline/candidate verification in a retained Blaxel sandbox. Returns a run_id; poll get_verification_result. Does not apply source edits.
The description explains the capability, when to use it, and what to expect.
Inputs8/100
4 of 38 inputs have descriptions. Add descriptions to the missing inputs, including where to obtain IDs and how to supply values.
server_url
Target baseline MCP endpoint; it must match the patch identity.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
patch › patch_id
Not provided
Missing description. Explain what this value means and how to supply it.
patch › base_server_version
Not provided
Missing description. Explain what this value means and how to supply it.
patch › base_source_hashes
Not provided
Missing description. Explain what this value means and how to supply it.
patch › base_tools_hash
Not provided
Missing description. Explain what this value means and how to supply it.
patch › candidate_tools › items › name
Not provided
Missing description. Explain what this value means and how to supply it.
patch › candidate_tools › items › description
Not provided
Missing description. Explain what this value means and how to supply it.
patch › candidate_tools_hash
Not provided
Missing description. Explain what this value means and how to supply it.
patch › wire_ops › items › oneOf › 0 › op
Not provided
Missing description. Explain what this value means and how to supply it.
patch › wire_ops › items › oneOf › 0 › tool
Not provided
Missing description. Explain what this value means and how to supply it.
patch › wire_ops › items › oneOf › 0 › value
Not provided
Missing description. Explain what this value means and how to supply it.
The title clearly communicates the tool’s action and subject. Keep it concise.
Description87/100
Use to read retained sandbox progress and complete verification results by run_id. Returns all trials and provisional verdict, or an explicit lifecycle status. No server instance state is required.
The description explains the capability, when to use it, and what to expect.
Inputs99/100
Input documentation gives an agent enough context to populate the arguments.
run_id
Run ID returned by verify_patch; poll this same ID until complete or failed.
A few tasks worth trying with this server, chosen from its reviewed tools. These have not been run.
01Audit MCP metadataUse to read live MCP tools/list and deployment identity, report deterministic metadata findings and provider-counted static tool tokens.
02Replay S8 milestoneUse to preview AX Lint's read-only verification viewer using the recorded live Railway run.
03Read verification resultUse to read retained sandbox progress and complete verification results by run_id.
04Check hostingUse to check AX Lint hosting: outbound HTTPS, configured secrets and access to the configured Blaxel proof sandbox.
Want to run these tasks against your MCP server with us?
AX Lint setup, tools, quality score, publishing readiness, and alternatives.
How do I add AX Lint to Claude, ChatGPT, or Cursor?
Add AX Lint 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://fast-pulse-rlqvb.run.mcp-use.com/mcp.
Is AX Lint MCP ready for ChatGPT and Claude?
As of October 18, 2026, AX Lint scores 90/100 on Manufact's MCP publishing checklist. The scan does not yet meet ChatGPT publishing checks and meets Claude publishing checks. Passing these checks does not guarantee marketplace approval.
How clear is AX Lint's MCP tool documentation?
As of October 18, 2026, AX Lint scores 79/100 in Manufact's review of tool titles, descriptions, input and output schemas, and behavior annotations. The review covers 7 of 7 discovered tools. The quality score measures documentation clarity; runtime behavior and marketplace readiness require separate checks.
What are the best alternatives to AX Lint?
As of October 19, 2026, alternatives to AX Lint in developer-tools on the Manufact MCP catalog include Held at the Gate, Speko, turva.dev, AgentMail, and Celesto Cloud Computers.
How can AX Lint improve its MCP documentation?
propose_patch is the lowest-scoring reviewed tool at 60/100. 2 of 23 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.
