AgentStatus MCP server for AI agents
Let Claude, ChatGPT or your own agent read AgentStatus: 2 typed functions through one MCP server. No AgentStatus API key needed.
- Site
- agentstatus.dev
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just AgentStatus
An MCP server for AgentStatus alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/agentstatusEvery site
One MCP server for AgentStatus and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 2
getServerReads one server's entry on the index by slug, including every tool the index probed and its invocation and functional success rates.Arguments
Name Type Required slugstringAgentstatus.dev/mcp-index/<slug> page URL.Yes Returns
GetServerResultinterface AgentStatusTool { name: string; description: string | null; invocationRate: number | null; functionalRate: number | null; // share whose result looked like the job, 0-100 } interface AgentStatusServer { slug: string; name: string; url: string; // the server's page on agentstatus.dev homepageUrl: string | null; category: string | null; categoryLabel: string | null; rank: number | null; score: number | null; // raw 0-100 MCP Reliability Index grade: "A" | "B" | "C" | "D" | "F" | null; // null when unrated unrated: boolean; lowSample: boolean; status: string | null; // e.g. "operational" uptime30d: number | null; toolSuccess: number | null; protocolConformance: number | null; latencyP95Ms: number | null; protocolVersion: string | null; totalRuns: number | null; toolCount: number | null; lastCheckedAt: string | null; scoreBreakdown: Record<string, number> | null; } interface GetServerResult extends AgentStatusServer { tools: AgentStatusTool[]; submitUrl: string; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/agentstatus/getServerCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.agentstatus.getServer({ slug: "cocktail-glass" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.agentstatus.getServer({"slug": "cocktail-glass"}))curl -X POST https://api.bowmark.ai/v1/sites/agentstatus/getServer \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"slug":"cocktail-glass"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.agentstatus.getServer({ slug: "cocktail-glass" });searchServersSearches the Public MCP Score index (agentstatus.dev/mcp-index) by server name, slug or domain.Arguments
Name Type Required querystringThe index matches names and domains, not URLs.Yes limitnumberDefault 10, max 50.No Returns
SearchServersResultinterface AgentStatusServer { slug: string; name: string; url: string; // the server's page on agentstatus.dev homepageUrl: string | null; category: string | null; categoryLabel: string | null; rank: number | null; score: number | null; // raw 0-100 MCP Reliability Index grade: "A" | "B" | "C" | "D" | "F" | null; // null when unrated unrated: boolean; lowSample: boolean; status: string | null; // e.g. "operational" uptime30d: number | null; toolSuccess: number | null; protocolConformance: number | null; latencyP95Ms: number | null; protocolVersion: string | null; totalRuns: number | null; toolCount: number | null; lastCheckedAt: string | null; scoreBreakdown: Record<string, number> | null; } interface SearchServersResult { query: string; lastUpdated: string | null; serversTracked: number | null; servers: AgentStatusServer[]; // [] when nothing on the index matches submitUrl: string; // the site's own "Submit your MCP server" form }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/agentstatus/searchServersCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.agentstatus.searchServers({ query: "cocktail" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.agentstatus.searchServers({"query": "cocktail"}))curl -X POST https://api.bowmark.ai/v1/sites/agentstatus/searchServers \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"cocktail"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.agentstatus.searchServers({ query: "cocktail" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/agentstatus/<function> - OpenAPI
/v1/sites/agentstatus/openapi.json