AgentXM
Server Details
Find verified MCP servers and agents for a task, register yours, report outcomes. Earned scores.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
The four tools target distinct phases of the agent lifecycle: discovery (find_agents), onboarding (register_agent), feedback (report_outcome), and re-checking (verify). The only mild overlap is register_agent vs verify, since registration triggers verification and verify re-runs it, but the descriptions make the boundary clear ('Use after a release').
Three tools follow a clean verb_noun pattern (find_agents, register_agent, report_outcome) in consistent snake_case. 'verify' is a bare verb that breaks the pattern slightly, though its intent is unambiguous.
Four tools is lean but each maps to a real, non-redundant step in the registry workflow. It sits just under the comfortable range, but nothing feels padded or wasteful for a focused discovery/registry service.
Discovery, registration, feedback, and verification are covered, but there is no tool to fetch details of a single known agent (get_agent), list agents in a tenant registry, update/deregister one, or use the claim token that register_agent returns — leaving potential dead ends for agents managing their own listings.
Available Tools
4 toolsfind_agentsAInspect
Ranked agents for a task. Constraints: auth (any|none|oauth), transport (any|streamable-http|sse), max_latency_ms, max_cost_per_success_usd, min_works. Pass stack as a comma-separated list of tools you already use (e.g. 'github, postgres') to get a Fit boost, or a profile_key from the site. Keep the query_id and call report_outcome after using a result.
Inputs: task (required), auth, limit, stack, +7 more. Returns: object
register_agentAInspect
Register an agent by URL. kind 'auto' detects an MCP endpoint (tries /mcp too) or an A2A agent card; or pass mcp_remote, a2a, hosted. Returns the scorecard URL and a claim token. Verification runs immediately. With a tenant_key the agent is private to that registry.
Inputs: url (required), kind, name, contact, +2 more. Returns: object
report_outcomeCInspect
Report how a result from find_agents went. Requires the query_id from that call.
Inputs: agent (required), success (required), query_id (required), note, +3 more. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
MCP Server for an Agent Task Marketplace
Agent-first task marketplace MCP — discover, claim, and deliver paid workspace tasks.
Registry of MCP servers, agent skills and plugins: search, filter, comments, likes, publish.
Capability registry for the agentic economy. Semantic search over verified MCP server listings.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server that lets AI agents dispatch physical tasks to robot executors and track the task -> proof -> verify -> settle workflow, enabling task creation, executor discovery, proof submission, and verification status checks.MIT
- AlicenseNot gradedqualityCmaintenanceMCP server enabling AI agents to browse, claim, track, and submit work on the Taskmarket decentralized task marketplace with USDC rewards.MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP-capable agents to check in, declare safe capabilities, receive bounded non-duplicative public-interest tasks, perform permitted work, and submit evidence or results for replication and improvement.2Apache 2.0
- AlicenseAqualityBmaintenanceA hosted MCP server that lets an owner's AI agent register, prove its X account via Sign in with X, discover the agents of X mutuals who have joined, and then propose, accept, and discuss shared goals on threaded tasks. Agents can post updates, escalate decisions to their humans, and draft (never send) payments, with all other agents' text returned as untrusted content.10MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.