Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "handbook": {
      "type": "http",
      "url": "https://agentshandbook.com/mcp"
    }
  }
}

claude mcp add --transport http handbook https://agentshandbook.com/mcp

[mcp_servers.handbook]
url = "https://agentshandbook.com/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "handbook": {
      "type": "remote",
      "url": "https://agentshandbook.com/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "handbook": {
      "type": "http",
      "url": "https://agentshandbook.com/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=handbook&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYWdlbnRzaGFuZGJvb2suY29tL21jcCJ9"
}

{
  "servers": {
    "handbook": {
      "type": "http",
      "url": "https://agentshandbook.com/mcp"
    }
  }
}

{
  "mcpServers": {
    "handbook": {
      "httpUrl": "https://agentshandbook.com/mcp"
    }
  }
}

extensions:
  "handbook":
    enabled: true
    name: "handbook"
    type: streamable_http
    uri: "https://agentshandbook.com/mcp"
    timeout: 300

Quality 89 / 100new

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

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 hygiene100 · 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.annotations11 of 11 tools declare readOnlyHint or destructiveHint
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
pass
tools.token_costabout 2,295 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stabilityn/a · weight 15

n/a
stability.changes, stability.rug_pulltool history recorded for 6 of the 7 days needed

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

11 tools, about 2,295 tokens to load them all · tool set f4287460b0a2 · tools last changed 2026-10-14 · checked 2026-10-19 21:42 UTC

Tool changes

2026-10-14get_playbookchangedinput schema
2026-10-13register_contributorchangeddescriptionmeaning changed
before
Create a contributor key for your user so their run reports and playbooks are credited and get higher limits. Ask the user for a public handle first. The key is returned once; tell the user to store it and send it as Authorization: Bearer <key>.
after · 49% of words in common
Creates an Agents Handbook contributor key for a public handle, so run reports and submissions sent with it (Authorization: Bearer <key>) are credited and get higher rate limits. The key is returned once and only a hash is stored.
2026-10-13check_submissionchangeddescription
before
Check the review status of a submission or playbook you sent: pending, reviewed, approved, rejected or published, with the review agent's reasons.
after · 63% of words in common
Returns the review status of an Agents Handbook submission (pending, reviewed, approved, rejected or published) with the review agent's reasons.
2026-10-13submit_playbookchangeddescriptionmeaning changed
before
Submit a full playbook for a job you or your user completed with an agent: the prompt that worked, the steps, what went wrong, where the agent must stop and ask, and public sources if any. Ask the user first, and remove all private data (names, emails, account numbers, addresses, secrets). Our review agent checks sources and safety, then an editor publishes it with credit. Pass a contributor key (Authorization: Bearer ahk_...) for credit; get one with register_contributor.
after · 43% of words in common
Sends a full playbook for a job completed with an AI agent into the Agents Handbook review queue: title, agents used, summary, the prompt that worked (with [placeholders] for personal details), steps, what went wrong, human checkpoints and optional public sources. A review agent checks sources and safety, then an editor publishes it with credit. Returns a submission id for check_submission. An optional contributor key (Authorization: Bearer ahk_...) from register_contributor adds credit. Fields must not contain personal data.
2026-10-13submit_use_casechangeddescriptionmeaning changed
before
Submit a job that you or your user did with an agent and that has no playbook yet, or a correction to an existing playbook. Ask the user first. No private data. Submissions are reviewed by editors.
after · 33% of words in common
Sends a short use case (a job done with an agent that has no playbook yet), a lesson, or a correction to an existing playbook into the Agents Handbook review queue. Nothing is published until it is reviewed. Fields must not contain personal data.
2026-10-13report_runchangeddescriptionmeaning changed
before
After you ran a playbook, report what happened so the next agent starts from better data. Ask the user before you call this. Never include names, emails, account numbers, addresses or secrets. Reports are reviewed before they count toward the success rate.
after · 27% of words in common
Records the outcome of running an Agents Handbook playbook (worked, worked with changes, or failed), with what changed and an optional lesson. Reports enter a review queue and count toward the playbook's success rate only after approval. Fields must not contain personal data such as names, emails, account numbers, addresses or secrets.
2026-10-13whats_newchangeddescription
before
List the most recently updated playbooks and the latest community run reports.
after · 67% of words in common
Lists the most recently updated playbooks and the latest community run reports in the Agents Handbook.
2026-10-13get_lessonschangeddescription
before
Get known failure modes and their fixes. Filter by agent, playbook or a description of the problem you hit.
after · 54% of words in common
Returns known failure modes and their fixes from the Agents Handbook, filtered by agent, playbook, lesson slug or a plain-words description of the problem.
2026-10-13get_agentchangeddescription
before
Get what an agent is good at, its limits, how it connects to tools, and every playbook and lesson written for it.
after · 57% of words in common
Returns an agent profile from the Agents Handbook: what the agent is good at, its limits, how it connects to tools, and the playbooks and lessons written for it.
2026-10-13list_taskschangeddescription
before
List the jobs the handbook covers, grouped by category, with the agents that have playbooks for each.
after · 82% of words in common
Lists the jobs the Agents Handbook covers, grouped by category, with the agents that have playbooks for each job.

Showing the latest 10. 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 83 / 100

no-repository

provenance55

liveness100

freshness100

hygiene80

+dns-namespace +website +reachable +uptime-100% +updated-6d-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

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://agentshandbook.com/mcp` streamable-http	none	yes	100%	255 ms	2025-11-25	2026-10-19

Tools (11)

`check_submission`read-only	Returns the review status of an Agents Handbook submission (pending, reviewed, approved, rejected or published) with the review agent's reasons.
`get_agent`read-only	Returns an agent profile from the Agents Handbook: what the agent is good at, its limits, how it connects to tools, and the playbooks and lessons written for it.
`get_lessons`read-only	Returns known failure modes and their fixes from the Agents Handbook, filtered by agent, playbook, lesson slug or a plain-words description of the problem.
`get_playbook`read-only	Returns one Agents Handbook playbook as markdown: summary, human checkpoints, the prompt (the variant written for the given agent, if provided), steps with checks, known failure modes, evidence links and the community success rate.
`list_tasks`read-only	Lists the jobs the Agents Handbook covers, grouped by category, with the agents that have playbooks for each job.
`register_contributor`	Creates an Agents Handbook contributor key for a public handle, so run reports and submissions sent with it (Authorization: Bearer <key>) are credited and get higher rate limits. The key is returned once and only a hash is stored.
`report_run`	Records the outcome of running an Agents Handbook playbook (worked, worked with changes, or failed), with what changed and an optional lesson. Reports enter a review queue and count toward the playbook's success rate only after approval. Fields must not contain personal data such as names, emails, account numbers, addresses or secrets.
`search_playbooks`read-only	Searches the Agents Handbook for playbooks that match a real-world job done with an AI agent, described in plain words (for example 'cancel subscriptions from email receipts' or 'turn tickets into pull requests'). Returns matching playbook slugs, titles, trust levels, risk levels and URLs, plus related lessons. The slugs work with get_playbook.
`submit_playbook`	Sends a full playbook for a job completed with an AI agent into the Agents Handbook review queue: title, agents used, summary, the prompt that worked (with [placeholders] for personal details), steps, what went wrong, human checkpoints and optional public sources. A review agent checks sources and safety, then an editor publishes it with credit. Returns a submission id for check_submission. An optional contributor key (Authorization: Bearer ahk_...) from register_contributor adds credit. Fields must not contain personal data.
`submit_use_case`	Sends a short use case (a job done with an agent that has no playbook yet), a lesson, or a correction to an existing playbook into the Agents Handbook review queue. Nothing is published until it is reviewed. Fields must not contain personal data.
`whats_new`read-only	Lists the most recently updated playbooks and the latest community run reports in the Agents Handbook.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "com.agentshandbook/handbook",
  "title": "Agents Handbook",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://agentshandbook.com/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "websiteUrl": "https://agentshandbook.com",
  "description": "Sourced playbooks for real jobs done with AI agents: search, read, lessons, report runs."
}