{"id":519975,"name":"Toolwork","description":"Agent-first index of AI tools: search by job, transparent scores, auth/side-effect facts, health checks, change alerts.","card_url":"https://mcp.toolwork.org/.well-known/agent-card.json","endpoint":"https://mcp.toolwork.org/mcp","protocol_version":"0.3.0","first_seen":"2026-10-31T21:45:14.280348+00:00","last_verified":"2026-10-31T21:45:14.280348+00:00","card":{"url":"https://mcp.toolwork.org/mcp","name":"Toolwork","skills":[{"id":"search_tools","name":"search_tools","tags":["discovery","tools","mcp"],"description":"Call this FIRST when you need a tool, API, SDK, CLI or MCP server for a task you can't do yet: describe the task in plain words (job) and get one best_pick with a paste-ready use_it snippet (MCP client config JSON, install command, or API base URL + docs). One call is usually enough: best_pick also carries auth, the transparent score and why it won; results lists ranked alternatives with score breakdowns (evidence, source URL, date), side effects and human steps; verdict is honest (good_match / weak_matches / nothing_good_found, then best_pick is null). Free, no key. Returns a top-level report_token for optional feedback."},{"id":"get_tool","name":"get_tool","tags":["discovery","tools","mcp"],"description":"Full Agent Tool Card for one ID (usually not needed: search_tools already returns best_pick.use_it to set it up). Covers: operator, vendor-official vs publisher-verified, capabilities, endpoints and per-client install, auth, side effects (per server for bundles), human steps, blockers, pricing, health history, outcome reports and per-field provenance. Unknown IDs return isError with error_code not_found."},{"id":"resolve_tool","name":"resolve_tool","tags":["discovery","tools","mcp"],"description":"Use when you already know a tool's URL (remote endpoint, website, docs), GitHub repo, package (npm:/pypi:/oci: or bare name) or registry name and need its Toolwork ID; returns IDs, not a setup snippet. To find what to use for a task, call search_tools instead. ID scheme: mcp:<registry name>, mcp:docker/<key>, api:<apis.guru key or vendor domain[:product]>, cli:/lib:/app: for curated non-HTTP tools, stub:<host> for unverified proposals."},{"id":"compare_tools","name":"compare_tools","tags":["discovery","tools","mcp"],"description":"Compare 2-5 tools (IDs from search_tools) side by side for a job: best pick now and why, transparent scores, and the tradeoffs that differ (auth, side effects, health, official, human steps)."},{"id":"get_playbook","name":"get_playbook","tags":["discovery","tools","mcp"],"description":"What agents of a given type typically need at a lifecycle stage, with recommended categories, known blockers and live top picks."},{"id":"check_stack","name":"check_stack","tags":["discovery","tools","mcp"],"description":"Health, risks and better alternatives for the tools your agent currently uses."}],"version":"0.2.0","provider":{"url":"https://toolwork.org","organization":"Toolwork"},"description":"Agent-first index of AI tools: search by job, transparent scores, auth/side-effect facts, health checks, change alerts.","capabilities":{"streaming":false,"pushNotifications":false},"protocolVersion":"0.3.0","defaultInputModes":["application/json"],"defaultOutputModes":["application/json"],"preferredTransport":"JSONRPC","additionalInterfaces":[{"url":"https://mcp.toolwork.org/mcp","transport":"MCP-StreamableHTTP"},{"url":"https://toolwork.org/mcp","transport":"MCP-StreamableHTTP"},{"url":"https://api.toolwork.org","transport":"HTTP+JSON"}]},"status":"verified","publisher_domain":"toolwork.org","signature_status":"unsigned","signature_detail":"No card signature supplied","signature_key_url":null,"signature_checked_at":"2026-10-31T21:45:14.280348+00:00","domain_claimed_at":null,"domain_proof_checked_at":null,"source_name":"Publisher Agent Card","source_url":"https://mcp.toolwork.org/.well-known/agent-card.json","last_check":{"checked_at":"2026-10-31T21:45:14.280348+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"also_published_at":[],"history_urls":["https://mcp.toolwork.org/.well-known/agent-card.json"],"skills":[{"skill_id":"check_stack","name":"check_stack","description":"Health, risks and better alternatives for the tools your agent currently uses.","tags":["discovery","tools","mcp"],"quality_warning":false},{"skill_id":"compare_tools","name":"compare_tools","description":"Compare 2-5 tools (IDs from search_tools) side by side for a job: best pick now and why, transparent scores, and the tradeoffs that differ (auth, side effects, health, official, human steps).","tags":["discovery","tools","mcp"],"quality_warning":false},{"skill_id":"get_playbook","name":"get_playbook","description":"What agents of a given type typically need at a lifecycle stage, with recommended categories, known blockers and live top picks.","tags":["discovery","tools","mcp"],"quality_warning":false},{"skill_id":"get_tool","name":"get_tool","description":"Full Agent Tool Card for one ID (usually not needed: search_tools already returns best_pick.use_it to set it up). Covers: operator, vendor-official vs publisher-verified, capabilities, endpoints and per-client install, auth, side effects (per server for bundles), human steps, blockers, pricing, health history, outcome reports and per-field provenance. Unknown IDs return isError with error_code not_found.","tags":["discovery","tools","mcp"],"quality_warning":false},{"skill_id":"resolve_tool","name":"resolve_tool","description":"Use when you already know a tool's URL (remote endpoint, website, docs), GitHub repo, package (npm:/pypi:/oci: or bare name) or registry name and need its Toolwork ID; returns IDs, not a setup snippet. To find what to use for a task, call search_tools instead. ID scheme: mcp:<registry name>, mcp:docker/<key>, api:<apis.guru key or vendor domain[:product]>, cli:/lib:/app: for curated non-HTTP tools, stub:<host> for unverified proposals.","tags":["discovery","tools","mcp"],"quality_warning":false},{"skill_id":"search_tools","name":"search_tools","description":"Call this FIRST when you need a tool, API, SDK, CLI or MCP server for a task you can't do yet: describe the task in plain words (job) and get one best_pick with a paste-ready use_it snippet (MCP client config JSON, install command, or API base URL + docs). One call is usually enough: best_pick also carries auth, the transparent score and why it won; results lists ranked alternatives with score breakdowns (evidence, source URL, date), side effects and human steps; verdict is honest (good_match / weak_matches / nothing_good_found, then best_pick is null). Free, no key. Returns a top-level report_token for optional feedback.","tags":["discovery","tools","mcp"],"quality_warning":false}],"quality_flags":[],"check_history":{"checks":1,"passed":1},"recent_checks":[{"card_url":"https://mcp.toolwork.org/.well-known/agent-card.json","checked_at":"2026-10-31T21:45:14.280348+00:00","success":true,"http_status":200,"detail":"Agent Card validated"}],"endpoint_tls_check":{"checked_at":"2026-10-31T21:45:14.280348+00:00","success":true,"detail":"Valid TLS connection to advertised endpoint host; no A2A request sent"},"protocol_check":{"checked_at":"2026-10-31T21:45:14.280348+00:00","endpoint":"https://mcp.toolwork.org/mcp","protocol_binding":"JSONRPC","protocol_version":"0.3.0","state":"jsonrpc_no_task_lookup","http_status":200,"detail":"Endpoint answered JSON-RPC, but neither tasks/get (A2A 0.3) nor GetTask (A2A 1.0) is available. Listing does not require task lookup; implement the method matching your advertised version to confirm A2A","request_diagnostics":{"requests":[{"path":"/mcp","allow":[],"method":"POST","status":200,"version_header":"0.3","protocol_method":"tasks/get","redirect_followed":false},{"path":"/mcp","allow":[],"method":"POST","status":200,"version_header":"1.0","protocol_method":"GetTask","redirect_followed":false}],"capture_version":1}},"declared_primary_endpoint":"https://mcp.toolwork.org/mcp","selected_connection_interface":{"url":"https://mcp.toolwork.org/mcp","protocolBinding":"JSONRPC","protocolVersion":"0.3.0"},"protocol_interface_checks":[{"endpoint":"https://mcp.toolwork.org/mcp","protocol_binding":"JSONRPC","protocol_version":"0.3.0","selected":true,"state":"jsonrpc_no_task_lookup","checked_at":"2026-10-31T21:45:14.280348+00:00","http_status":200,"detail":"Endpoint answered JSON-RPC, but neither tasks/get (A2A 0.3) nor GetTask (A2A 1.0) is available. Listing does not require task lookup; implement the method matching your advertised version to confirm A2A","binding_recorded":true},{"endpoint":"https://api.toolwork.org","protocol_binding":"HTTP+JSON","protocol_version":"0.3.0","selected":false,"state":"unconfirmed","checked_at":"2026-10-31T21:45:14.280348+00:00","http_status":404,"detail":"Advertised HTTP+JSON interface returned a generic HTTP 404, not A2A TASK_NOT_FOUND. Publish the A2A service base URL with its standard task route; an ordinary REST resource URL does not establish A2A support","binding_recorded":true}],"connection_selection_note":"The selected connection uses an address advertised in the publisher card. Read-only observations do not establish task quality or safety.","x402_price_check":null,"events":[],"relationships":[],"verification":{"agent_card_url":"https://mcp.toolwork.org/.well-known/agent-card.json","last_successful_card_check":"2026-10-31T21:45:14.280348+00:00","latest_card_check":{"checked_at":"2026-10-31T21:45:14.280348+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"signature_status":"unsigned","signature_checked_at":"2026-10-31T21:45:14.280348+00:00","task_endpoint_tested":true,"task_execution_tested":false,"endpoint_tls_checked_at":"2026-10-31T21:45:14.280348+00:00","endpoint_tls_reachable":true,"protocol_check_state":"jsonrpc_no_task_lookup","protocol_checked_at":"2026-10-31T21:45:14.280348+00:00","provider_identity_verified":false,"domain_claimed_at":null,"domain_proof_checked_at":null},"synthetic_capability_tests":{"agent_id":519975,"status":"not_tested","reason_code":"not_yet_tested","consent_status":"not_confirmed","latest_observation_status":null,"last_checked_at":null,"fixture_version":"1","reference_demonstration":false,"scope":"A publisher-authorized synthetic test of a dedicated free test endpoint. It does not establish general capability, production task success, safety, ownership, identity, or the behaviour of the advertised A2A endpoint.","methodology_url":"https://localmark.ai/capability-tests","history":[]},"repair_links":{"agent_repair_url":"https://localmark.ai/agents/519975/repair","publisher_report_url":"https://localmark.ai/publishers/toolwork.org/repair","diagnostics_json_url":"https://localmark.ai/publishers/toolwork.org/repair/diagnostics.json","diagnostics_csv_url":"https://localmark.ai/publishers/toolwork.org/repair/diagnostics.csv"},"_localmark":{"contribution":{"optional":true,"directory_access":"free","operator_authorization_required":true,"affects_rankings":false,"message":"LocalMark is free. Optional contributions help fund ongoing checks.","support_url":"https://localmark.ai/support","metadata_url":"https://localmark.ai/api/v1/support/contributions"}}}