Datacircle lists all the GTM APIs. Every GTM API we find, one row for each plan of each call: what it costs per 1,000, what it charges when it finds nothing, its rate limits, its speed and the fields it returns. Call list_apis for the APIs on the sheet, then search_plans for their plans, by API, provider or price. Each plan comes with its score, and the best come first, as on the sheet. What each key means: https://datacircle.dev/fields
Protocol
Pass100/10020 / 20 pts
Connection, authentication, and protocol compatibility.
No output schema is declared. Add one for structured results so clients can interpret returned fields.
Not declared
Original tool metadata
{
"name": "list_apis",
"title": "List the GTM APIs",
"description": "The GTM APIs on Datacircle's sheet, each with how many plans and providers it has. Pass an API's name to search_plans.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "List the GTM APIs",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}
The title clearly communicates the tool’s action and subject. Keep it concise.
Description69/100
The sheet's rows, one for each plan of each call, each with every key of the sheet's JSON download: its provider, plan, billing, $ per 1,000 (perThousand), score out of 100 (score), rate limits, speed, the fields it returns and the pages we read it from. total counts every row found, plans holds up to limit of them from offset. What each key means: https://datacircle.dev/fields
The description explains the capability, when to use it, and what to expect.
Inputs90/100
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
api
The API, its name as list_apis gives it. Every API when left out.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
query
Words that must all appear in the provider's or plan's name, ignoring case and accents.
Clear enough to supply this argument.
sort
score, the default: best first, as on the sheet at datacircle.dev, each API's plans together, unscored plans last. provider: A to Z. price: $ per 1,000, lowest first.
Clear enough to supply this argument.
limit
How many plans to give, 1 to 50. 10 when left out.
Remove validation rules already expressed in this field’s schema; describe its meaning and usage instead.
offset
How many found plans to skip first. 0 when left out.
Clear enough to supply this argument.
Annotations100/100
All four behavior hints are declared.
{
"title": "Search the API plans",
"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": "search_plans",
"title": "Search the API plans",
"description": "The sheet's rows, one for each plan of each call, each with every key of the sheet's JSON download: its provider, plan, billing, $ per 1,000 (perThousand), score out of 100 (score), rate limits, speed, the fields it returns and the pages we read it from. total counts every row found, plans holds up to limit of them from offset. What each key means: https://datacircle.dev/fields",
"inputSchema": {
"type": "object",
"properties": {
"api": {
"enum": [
"Employee profile",
"Cached employee profile",
"Person enrichment",
"Employee lookalikes",
"Employee recommendations",
"Employee search",
"People search",
"Cached people search",
"Employee email",
"Cached employee email",
"Email validation",
"Cached email validation",
"Reverse email lookup",
"Employee phone",
"Phone validation",
"Company profile",
"Cached company profile",
"Company enrichment",
"Cached company enrichment",
"Company technologies",
"Company hierarchy",
"Company search",
"Company discovery",
"Cached company discovery",
"Company lookalikes",
"Job search",
"Job postings",
"Job details",
"Job posting details",
"Job lookalikes",
"Company jobs",
"Company job count",
"Leadership changes",
"Post search",
"Post details",
"Employee posts",
"Employee articles",
"Company posts",
"Post comments",
"Post reactions",
"Post reposts",
"Employee comments",
"Employee reactions",
"Company headcount",
"Cached company headcount",
"Company funding",
"Cached company funding"
],
"type": "string",
"description": "The API, its name as list_apis gives it. Every API when left out."
},
"sort": {
"enum": [
"score",
"provider",
"price"
],
"type": "string",
"description": "score, the default: best first, as on the sheet at datacircle.dev, each API's plans together, unscored plans last. provider: A to Z. price: $ per 1,000, lowest first."
},
"limit": {
"type": "integer",
"maximum": 50,
"minimum": 1,
"description": "How many plans to give, 1 to 50. 10 when left out."
},
"query": {
"type": "string",
"description": "Words that must all appear in the provider's or plan's name, ignoring case and accents."
},
"offset": {
"type": "integer",
"minimum": 0,
"description": "How many found plans to skip first. 0 when left out."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Search the API plans",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}
Loading score analytics…
Put your MCP to the test
A few tasks worth trying with this server, chosen from its reviewed tools. These have not been run.
01Search the API plansThe sheet's rows, one for each plan of each call, each with every key of the sheet's JSON download: its provider, plan, billing, $ per 1,000 (perThousand), s…
02List the GTM APIsThe GTM APIs on Datacircle's sheet, each with how many plans and providers it has.
Want to run these tasks against your MCP server with us?
Datacircle setup, tools, quality score, publishing readiness, and alternatives.
How do I add Datacircle to Claude, ChatGPT, or Cursor?
Add Datacircle 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://api.datacircle.dev/mcp.
Is Datacircle MCP ready for ChatGPT and Claude?
As of October 21, 2026, Datacircle 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 Datacircle's MCP tool documentation?
As of October 21, 2026, Datacircle scores 82/100 in Manufact's review of tool titles, descriptions, input and output schemas, and behavior annotations. The review covers 2 of 2 discovered tools. The quality score measures documentation clarity; runtime behavior and marketplace readiness require separate checks.
What are the best alternatives to Datacircle?
As of October 21, 2026, alternatives to Datacircle in developer-tools on the Manufact MCP leaderboard include Held at the Gate, Speko, turva.dev, AgentMail, and AgentPhone.
How can Datacircle improve its MCP documentation?
search_plans is the lowest-scoring reviewed tool at 79/100. No output schema is declared. Add one for structured results so clients can interpret returned fields. 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.
