Agents Handbook

com.agentshandbookPublished by agentshandbook.comOfficial publisherv1.0.0Updated Oct 24, 2026

Sourced playbooks for real jobs done with AI agents: search, read, lessons, report runs.

VerifiedStreamable HTTPWeb executableProductivity & WorkflowKnowledge & Memory

Overview

AI-generated overview

A remote MCP server for the Agents Handbook: search and read agent playbooks, lessons and agent profiles, and submit run reports or new playbooks for review.

What you can do
Search and read playbooks for real jobs done with AI agents, including trust and risk levels, prompts, steps and success rates, and list covered tasks by category with their agents. Look up agent profiles covering strengths, limits and tool connections, and retrieve known failure modes with fixes. Check recently updated playbooks and community run reports. Report the outcome of a playbook run, or submit a use case, lesson, correction or full playbook to a review queue, then check its review status. Register a contributor key for a public handle so submissions are credited.
When to use it
Useful when an assistant is planning or executing a real-world task with an agent and wants a sourced, community-reviewed playbook, known failure modes, or agent-specific guidance, and when you want to contribute results back to the handbook.
Requirements
A remote streamable HTTP endpoint at agentshandbook.com; no package, environment variables or headers are declared. Registering a contributor key is optional and returns a bearer token used for crediting and higher rate limits.
Before you install
Submissions and run reports are sent to a third-party service and enter a review queue; nothing is published until reviewed. Fields must not contain personal data such as names or emails, and prompts should use placeholders for personal details. The contributor key is returned only once, so store it safely.

Installation

In SourceWeft

  1. Open Agents Handbook in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.agentshandbook%2Fhandbook/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

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

Tools

11

search_playbooks

Search playbooks

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.

Parametersagentlimitqueryrequiredcategorymin_trust

get_playbook

Get a playbook

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.

Parametersslugrequiredagentinclude_attribution

list_tasks

List jobs

Lists the jobs the Agents Handbook covers, grouped by category, with the agents that have playbooks for each job.

Parameterscategory

get_agent

Get an agent profile

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.

Parametersslugrequired

get_lessons

Get lessons

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.

Parametersslugagentqueryplaybook

whats_new

What's new

Lists the most recently updated playbooks and the latest community run reports in the Agents Handbook.

Parameterslimit

report_run

Report a 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.

Parametersagentrequiredmodellessonoutcomerequiredplaybookrequiredreporterwhat_changedagent_versionduration_minutes

submit_use_case

Submit a 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.

Parametersbodyrequiredkindagenttitlerequiredplaybookreportersource_url

submit_playbook

Submit a 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.

Parametersjobstepsrequiredtitlerequiredagentsrequiredpromptrequiredoutcomesourcessummaryrequiredcategorytime_takenagent_versionwhat_went_wrong+1 more

check_submission

Check a submission

Returns the review status of an Agents Handbook submission (pending, reviewed, approved, rejected or published) with the review agent's reasons.

Parametersidrequired

register_contributor

Register as a 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.

Parametersemailhandlerequired

Version history

1
  1. v1.0.0LatestOct 13, 2026

Score

72% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.