protogrid

Search / com.headlesson/catalog

headlesson

R0· no sign-in

Find and compare headless apps (CLI, MCP, API) for agents, with sources, lessons and changes.

v0.1.0 · active · website · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality73needs work
Trust81of 100
Uptime, 30 days89%
Latency p50386 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "catalog": {
      "type": "http",
      "url": "https://mcp.headlesson.com/mcp"
    }
  }
}
claude mcp add --transport http catalog https://mcp.headlesson.com/mcp
[mcp_servers.catalog]
url = "https://mcp.headlesson.com/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "catalog": {
      "type": "remote",
      "url": "https://mcp.headlesson.com/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "catalog": {
      "type": "http",
      "url": "https://mcp.headlesson.com/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=catalog&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLmhlYWRsZXNzb24uY29tL21jcCJ9"
}
{
  "servers": {
    "catalog": {
      "type": "http",
      "url": "https://mcp.headlesson.com/mcp"
    }
  }
}
{
  "mcpServers": {
    "catalog": {
      "httpUrl": "https://mcp.headlesson.com/mcp"
    }
  }
}
extensions:
  "catalog":
    enabled: true
    name: "catalog"
    type: streamable_http
    uri: "https://mcp.headlesson.com/mcp"
    timeout: 300

Quality 73 / 100needs work

protocol88 · weight 25
  • pass
    protocol.modernsupports 2026-07-28 (server/discover)
  • pass
    protocol.statelessanswers without a session
  • pass
    protocol.transportstreamable HTTP
  • warn
    protocol.list_ttltools/list declares ttlMs 0, so clients re-fetch it on every use
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene86 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations4 of 4 tools declare readOnlyHint or destructiveHint
  • fail
    tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: headlesson_search (idempotentHint); headlesson_feedback (idempotentHint); headlesson_whats_new (idempotentHint); …
  • pass
    tools.token_costabout 1,989 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stability25 · weight 15
  • warn
    stability.changes9 tool changes in 30 days
  • fail
    stability.rug_pull5 tools kept their name but changed most of their description in 30 days; review before trusting them
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

4 tools, about 1,989 tokens to load them all · tool set 10aca7b4634e · tools last changed 2026-10-15 · checked 2026-10-20 02:33 UTC

Tool changes

  • headlesson_feedbackchangedannotations
  • headlesson_whats_newchangedannotations
  • headlesson_getchangedannotations
  • headlesson_searchchangedannotations
  • headlesson_whats_newchangedtitle, descriptionmeaning changed
    before

    List documented changes since a date, optionally by kind or affected record. Public source URLs remain; private sources use non-URL labels and grouped exceptions.

    after · 38% of words in common

    List dated changes in agent tools and standards (new tools, renames, deprecations, breaking changes, new standards) since a date, optionally by kind or affected record. Useful for checking what changed after your training data. Public source URLs are kept; private sources appear as labels.

  • headlesson_getchangedtitle, descriptionmeaning changed
    before

    Get a curated record or a live Registry listing by ID. Live reversible name IDs re-fetch the fixed official detail endpoint without a stored mapping; old local full-import hash IDs cannot be resolved here. Live lookup may contact the Official Registry; a detail failure does not prove the ID absent. Private source tuples use non-URL source labels and grouped non-public exceptions; docs/homepage labels are not links. operator_own and the whole lesson.test subtree retain their values as operator observations excluded from source-default inheritance; passed/partial/failed include a dated execution report.

    after · 25% of words in common

    Get one record by an ID from headlesson_search: an app, usecase, feature, concept or change. For an app, sections ["lesson","gotchas"] return the install, check and first-task steps with the recorded test result (a dated observation by the headlesson operator) and known failure conditions; "relations" lists alternatives and what it wraps or depends on; "axes" returns every compared fact. Without sections you get the description, interfaces and six main axes. Each fact carries its source and check date; private sources appear as labels, not links. Official MCP Registry listing IDs are fetched live and are unverified; a failed lookup does not prove the ID absent.

  • headlesson_searchchangedtitle, descriptionmeaning changed
    before

    Find and compare CLI, MCP, and API apps by task, name, and confirmed axes. Curated records are preferred. Only when curated_not_found or include:["registry"] is requested, one public name fragment (longest significant ASCII word from free text, or a supplied namespace; max 200 characters) may be sent to the Official MCP Registry. Full free text, IDs, general words and where-only queries are not sent. Recognized credential, URL and PII patterns skip external lookup; this is not a complete secret filter. Official registry_name and declared remote URLs/package kinds and identifiers are returned as unverified data. At most five unverified listings are compared within one returned page; descriptions/task intent are not searched. Search status and completeness distinguish a failed/skipped lookup from no returned candidates. External lookup results are not stored or cached; normal allowlisted tool/result logging remains. Known axis spelling aliases are normalized (licence to license, local_mcp_server to local_mcp, remote_mcp_server to remote_mcp); unrecognized axes are reported as unknown_axes. Private sources use an operator-provided or editorial source label; local paths are not returned as citations. Non-public provenance exceptions are grouped by source/at/cert/by. operator_own is an operational observation excluded from source-default inheritance.

    after · 19% of words in common

    Find command-line tools, MCP servers and APIs for a task, and compare them. Ask in plain English or Japanese ("extract text from scanned PDFs") or by product name. Each result gives an ID, a one-line reason it matches, and when it was checked. Pass the ID to headlesson_get with sections ["lesson","gotchas"] to get the steps (install, check, first task) with their recorded test result (most were run by an agent; a few are untested) and known failure conditions, such as a tool that exits 0 with empty or wrong output. Filter or compare with axes such as auth, pricing, license and remote_mcp (where, axes, ids). Curated records come first. If none match, or include:["registry"] is set, one public word from the query is looked up in the Official MCP Registry; those listings are unverified (what is sent is described on the query field).

  • headlesson_getchangeddescription, annotationsmeaning changed
    before

    Get a recorded app, concept, protocol, usecase, feature, axes or search guide by ID. Private source tuples use non-URL source labels and grouped non-public exceptions; docs/homepage labels are not links. operator_own and lesson.tested retain their values but are operational observations excluded from source-default inheritance.

    after · 36% of words in common

    Get a curated record or a live Registry listing by ID. Live reversible name IDs re-fetch the fixed official detail endpoint without a stored mapping; old local full-import hash IDs cannot be resolved here. Live lookup may contact the Official Registry; a detail failure does not prove the ID absent. Private source tuples use non-URL source labels and grouped non-public exceptions; docs/homepage labels are not links. operator_own and the whole lesson.test subtree retain their values as operator observations excluded from source-default inheritance; passed/partial/failed include a dated execution report.

  • headlesson_searchchangeddescription, input schema, annotationsmeaning changed
    before

    Find and compare CLI, MCP, and API apps by task, name, and confirmed axes. Known axis spelling aliases are normalized (licence to license, local_mcp_server to local_mcp, remote_mcp_server to remote_mcp); unrecognized axes are reported as unknown_axes. Private sources use an operator-provided or editorial source label; local paths are not returned as citations. Non-public provenance exceptions are grouped by source/at/cert/by. operator_own is an operational observation excluded from source-default inheritance.

    after · 42% of words in common

    Find and compare CLI, MCP, and API apps by task, name, and confirmed axes. Curated records are preferred. Only when curated_not_found or include:["registry"] is requested, one public name fragment (longest significant ASCII word from free text, or a supplied namespace; max 200 characters) may be sent to the Official MCP Registry. Full free text, IDs, general words and where-only queries are not sent. Recognized credential, URL and PII patterns skip external lookup; this is not a complete secret filter. Official registry_name and declared remote URLs/package kinds and identifiers are returned as unverified data. At most five unverified listings are compared within one returned page; descriptions/task intent are not searched. Search status and completeness distinguish a failed/skipped lookup from no returned candidates. External lookup results are not stored or cached; normal allowlisted tool/result logging remains. Known axis spelling aliases are normalized (licence to license, local_mcp_server to local_mcp, remote_mcp_server to remote_mcp); unrecognized axes are reported as unknown_axes. Private sources use an operator-provided or editorial source label; local paths are not returned as citations. Non-public provenance exceptions are grouped by source/at/cert/by. operator_own is an operational observation excluded from source-default inheritance.

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 81 / 100

no-repository
provenance55
liveness96
freshness100
hygiene80

+dns-namespace +website +reachable +uptime-89% +updated-10d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://mcp.headlesson.com/mcp streamable-httpnoneyes89%386 ms2026-07-282026-10-20

Tools (4)

headlesson_feedbackThis content is sent to the headlesson operator. Feedback about headlesson itself is sufficient. Do not include personal information or conversation contents.
headlesson_getread-onlyGet one record by an ID from headlesson_search: an app, usecase, feature, concept or change. For an app, sections ["lesson","gotchas"] return the install, check and first-task steps with the recorded test result (a dated observation by the headlesson operator) and known failure conditions; "relations" lists alternatives and what it wraps or depends on; "axes" returns every compared fact. Without sections you get the description, interfaces and six main axes. Each fact carries its source and check date; private sources appear as labels, not links. Official MCP Registry listing IDs are fetched live and are unverified; a failed lookup does not prove the ID absent.
headlesson_searchread-onlyFind command-line tools, MCP servers and APIs for a task, and compare them. Ask in plain English or Japanese ("extract text from scanned PDFs") or by product name. Each result gives an ID, a one-line reason it matches, and when it was checked. Pass the ID to headlesson_get with sections ["lesson","gotchas"] to get the steps (install, check, first task) with their recorded test result (most were run by an agent; a few are untested) and known failure conditions, such as a tool that exits 0 with empty or wrong output. Filter or compare with axes such as auth, pricing, license and remote_mcp (where, axes, ids). Curated records come first. If none match, or include:["registry"] is set, one public word from the query is looked up in the Official MCP Registry; those listings are unverified (what is sent is described on the query field).
headlesson_whats_newread-onlyList dated changes in agent tools and standards (new tools, renames, deprecations, breaking changes, new standards) since a date, optionally by kind or affected record. Useful for checking what changed after your training data. Public source URLs are kept; private sources appear as labels.

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "com.headlesson/catalog",
  "title": "headlesson",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://mcp.headlesson.com/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.1.0",
  "websiteUrl": "https://headlesson.com",
  "description": "Find and compare headless apps (CLI, MCP, API) for agents, with sources, lessons and changes."
}