MCPExplorer MCP

An MCP server that indexes, verifies, and scores trust for other MCP servers. It allows agents to search the server index, compare tools, check risk labels, generate runtime configurations, and plan toolsets based on plain-language goals.

Visit MCPExplorer

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by MCPExplorer

MCP endpoint (Streamable HTTP)

https://mcpexplorer.com/mcp

Vendor documentation

What its tools do

14 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (14)

search_servers
get_server
get_capability
compare_servers
generate_runtime_config
check_trust
get_alternatives
list_loadouts
get_loadout
list_capabilities
get_ecosystem_stats
list_runtimes
plan_toolset
report_broken_server

14 of 14 have a description · 0 of 14 declare behavior hints · 11 of 11 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 6, 2026, 5:41 PM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Search the MCP server index by capability or risk level
Generate runtime configuration for a specific server
Check explainable trust scores and risk labels
Plan a governed toolset from a plain-language goal

Source and maintenance

Community listingRegistry 1.0.0

mcp-registry: io.github.mcpexplorer/mcpexplorer@1.0.0 Source repository Project website

Maintenance checked: Nov 6, 2026, 5:06 PM UTC

Protocol and capabilities

Server: mcpexplorer 1.0.0
MCP protocol negotiated in check: 2025-11-25
Tools: 14 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": true
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

MCPExplorer — the trust and capability graph for MCP servers (mcpexplorer.com). An MCP for everything: search ~1,000 indexed servers, check explainable trust scores and per-tool risk labels, compare servers, and plan governed toolsets. No auth required — all 14 tools are free and read-only except report_broken_server (writes a moderation submission). Start with: search_servers (find by capability or text) · plan_toolset (goal → governed kit) · check_trust (explainable score + risk) · get_loadout (curated kits with plays). generate_runtime_config emits install config for your runtime.

Tools

14 advertised

search_servers — Search MCP servers

Advertised by the server during the last successful anonymous check.

Search the MCPExplorer index of MCP servers by free text and filters. Omit `query` to browse the whole index ranked by trust score. Every filter either applies or is echoed back in `ignored_filters` with a reason — filters never silently do nothing.

search_servers input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "Max results (default 10)"
    },
    "query": {
      "type": "string",
      "description": "Free-text query, e.g. 'send email' or 'postgres'. Omit to browse the full index ranked by trust."
    },
    "transport": {
      "enum": [
        "stdio",
        "sse",
        "streamable_http",
        "websocket",
        "unknown"
      ],
      "type": "string",
      "description": "Filter by transport. Many servers are still 'unknown' (transport not yet probed by the crawler)."
    },
    "capability": {
      "type": "string",
      "description": "Filter to servers providing a capability slug, e.g. 'send-email'. An unknown slug is reported in ignored_filters, not silently dropped."
    },
    "risk_level": {
      "enum": [
        "read-only",
        "read",
        "write",
        "destructive"
      ],
      "type": "string",
      "description": "Filter by tool risk. 'read-only' = has tools and none are write/destructive — the safe set to hand an autonomous agent."
    },
    "official_status": {
      "enum": [
        "official",
        "partner",
        "community",
        "unknown"
      ],
      "type": "string",
      "description": "Filter by provenance"
    }
  },
  "additionalProperties": false
}

get_server — Get an MCP server

Advertised by the server during the last successful anonymous check.

Fetch the full record for one MCP server by slug: install methods, tools, trust, verification, and provenance.

get_server input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Server slug, e.g. 'github'"
    }
  },
  "additionalProperties": false
}

get_capability — Get a capability

Advertised by the server during the last successful anonymous check.

List the best MCP servers that provide a capability (e.g. 'send-email', 'web-search'), ranked by trust.

get_capability input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Capability slug, e.g. 'send-email'"
    }
  },
  "additionalProperties": false
}

compare_servers — Compare two MCP servers

Advertised by the server during the last successful anonymous check.

Compare two MCP servers side by side: trust, transport, tools, install, and links.

compare_servers input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "a",
    "b"
  ],
  "properties": {
    "a": {
      "type": "string",
      "description": "First server slug"
    },
    "b": {
      "type": "string",
      "description": "Second server slug"
    }
  },
  "additionalProperties": false
}

generate_runtime_config — Generate MCP setup config

Advertised by the server during the last successful anonymous check.

Generate the install + client config for an MCP server in a given runtime (claude-desktop, cursor, vscode, windsurf, cline, continue, goose, openai-agents, langgraph, crewai).

generate_runtime_config input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "slug",
    "runtime"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Server slug"
    },
    "runtime": {
      "type": "string",
      "description": "Runtime slug, e.g. 'claude-desktop'"
    }
  },
  "additionalProperties": false
}

check_trust — Check trust

Advertised by the server during the last successful anonymous check.

Return the explainable trust score, label, scoring reasons, and verification history for an MCP server.

check_trust input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Server slug"
    }
  },
  "additionalProperties": false
}

get_alternatives — Get alternatives

Advertised by the server during the last successful anonymous check.

Find verified MCP servers with the same capabilities as a given server, ranked by trust.

get_alternatives input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Server slug"
    }
  },
  "additionalProperties": false
}

list_loadouts — List loadouts

Advertised by the server during the last successful anonymous check.

List curated loadouts — deliberately-assembled kits of MCP servers + governance + plays for a specific job (GTM, coding, research, support, infra). The agent-facing version of the /loadouts product. Use get_loadout for the full kit with live trust.

list_loadouts input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}

get_loadout — Get a loadout

Advertised by the server during the last successful anonymous check.

Fetch one curated loadout: its servers (each with role + LIVE trust/transport/tool-risk from the index), an aggregated governance posture for the whole kit, and the plays (see→decide→act sequences) it's designed to run.

get_loadout input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Loadout slug, e.g. 'gtm', 'coding', 'research'"
    }
  },
  "additionalProperties": false
}

list_capabilities — List capabilities

Advertised by the server during the last successful anonymous check.

List the capability slugs an agent can filter or look up by (e.g. 'send-email', 'query-database'), most-populated first. Use these with get_capability or search_servers' capability filter — the taxonomy isn't guessable.

list_capabilities input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Max capabilities (default 30)"
    }
  },
  "additionalProperties": false
}

get_ecosystem_stats — Get ecosystem stats

Advertised by the server during the last successful anonymous check.

Live snapshot of the indexed MCP ecosystem: totals (servers, tools, handshake-verified), provenance and transport breakdowns, and the current top-trust / most-adopted / newest / biggest-trust-riser servers.

get_ecosystem_stats input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}

list_runtimes — List runtimes

Advertised by the server during the last successful anonymous check.

List the runtimes generate_runtime_config supports (Claude Desktop, Cursor, VS Code, agent frameworks, …), with each one's config path. Enumerate these instead of guessing runtime slugs.

list_runtimes input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}

plan_toolset — Plan a governed toolset

Advertised by the server during the last successful anonymous check.

Turn a plain-language goal into a recommended, governed toolset: the best-fit curated loadout (matched transparently by goal terms) plus an assembled set of the most relevant indexed servers, each with LIVE trust and tool-risk, and an aggregate governance posture for the kit. The decision layer over search/capability/trust/loadouts.

plan_toolset input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "goal"
  ],
  "properties": {
    "goal": {
      "type": "string",
      "minLength": 3,
      "description": "What the agent should do, in plain language, e.g. 'triage support tickets and file bugs'."
    },
    "limit": {
      "type": "integer",
      "maximum": 10,
      "minimum": 1,
      "description": "Max assembled servers (default 6)."
    },
    "risk_tolerance": {
      "enum": [
        "any",
        "read-only"
      ],
      "type": "string",
      "description": "'read-only' restricts the assembled set to servers with no write/destructive tools — the safe set for an unsupervised agent. Default 'any'."
    }
  },
  "additionalProperties": false
}

report_broken_server — Report a broken server

Advertised by the server during the last successful anonymous check.

Report that an MCP server's install, docs, or endpoint is broken. Creates a submission for editorial review.

report_broken_server input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "slug",
    "detail"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Server slug"
    },
    "detail": {
      "type": "string",
      "maxLength": 1000,
      "description": "What's broken (install fails, endpoint down, docs wrong, …)"
    }
  },
  "additionalProperties": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (2 of 2 answered).

2026-11-06: 1 of 1 checks answered
2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 734 ms
95th percentile latency: 734 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 6, 2026, 5:41 PM UTC · probe · passed · 734 ms · metadata changed · 14 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http mcpexplorer-mcp https://mcpexplorer.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add mcpexplorer-mcp --url https://mcpexplorer.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable mcpexplorer-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "mcpexplorer-mcp": {
      "url": "https://mcpexplorer.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "mcpexplorer-mcp": {
      "type": "streamableHttp",
      "url": "https://mcpexplorer.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start mcpexplorer-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "mcpexplorer-mcp": {
      "type": "http",
      "url": "https://mcpexplorer.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http mcpexplorer-mcp https://mcpexplorer.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://mcpexplorer.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "mcpexplorer-mcp": {
      "serverUrl": "https://mcpexplorer.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like MCPExplorer MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows