Koskamo

runx MCP

The runx MCP server provides public read-only discovery of agent skills, allowing agents to search the catalog, inspect skill manifests, trust summaries, and fetch install commands without authentication. It serves as an adoption surface for the governed runtime, separating public discovery from authenticated mutation which remains on the controlled plane.

Visit runx

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.

runx MCP logo, by runxVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by runx
MCP endpoint (Streamable HTTP)
https://api.runx.ai/mcp
Vendor documentation

What its tools do

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

Read-only (2)

2 of 2 have a description · 2 of 2 declare behavior hints · 2 of 2 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to runx.ai ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Search the skill catalog for available agent skills
  • Inspect skill manifests and trust summaries
  • Fetch install commands for specific skills

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: ai.runx/runx@1.0.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
runx 1.0.0
MCP protocol negotiated in check
2025-11-25
Tools
2 advertised
Resources
0 advertised
Resource templates
1 advertised
Prompts
4 advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  },
  "prompts": {
    "listChanged": true
  },
  "resources": {
    "listChanged": true
  }
}

Server-provided instructions

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

Use this server to find a runx skill and read it before running anything. search_skills finds candidates by what they do. get_skill returns one skill in full: its manifest, the authority it asks for, its trust signals, and the exact command to install it through the runx CLI. Show a caller the requested authority and trust tier before you suggest running a skill. This surface is read-only, so nothing here executes a skill, moves money, or changes state; execution happens through the runx CLI or the authenticated hosted API, both of which apply policy and seal a receipt.

Tools

2 advertised

search_skills — Search runx skills
Advertised by the server during the last successful anonymous check.
Advertised read-only

Find runx skills by what they do. Returns each match with its skill id, publisher, description, latest version, and trust tier, so a caller can pick one and then read it in full with get_skill.

search_skills input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 9007199254740991,
      "description": "Maximum matches to return.",
      "exclusiveMinimum": 0
    },
    "query": {
      "type": "string",
      "description": "What the skill should do, in plain words. An empty string browses everything."
    }
  }
}
search_skills annotations
{
  "title": "Search runx skills",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_skill — Inspect runx skill
Advertised by the server during the last successful anonymous check.
Advertised read-only

Read one runx skill in full before running it: its manifest, the authority it asks for, its publisher and trust signals, and the exact command to install and run it through the runx CLI. Everything needed to decide whether to trust a skill arrives in this one call.

get_skill input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "skill_id"
  ],
  "properties": {
    "version": {
      "type": "string",
      "description": "Exact version to read. Defaults to the latest published version."
    },
    "skill_id": {
      "type": "string",
      "minLength": 1,
      "description": "Skill id in publisher/name form, for example `ausca/browser-session`."
    }
  }
}
get_skill annotations
{
  "title": "Inspect runx skill",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

4 advertised

install_skill — Install a skill

Advertised by the server during the last successful anonymous check.

Install a runx skill safely: check what it asks for before running it.

skill
Registry skill id to inspect and install.
author_skill — Author a skill

Advertised by the server during the last successful anonymous check.

Write a portable runx skill with typed inputs and explicit authority.

No arguments advertised.

publish_skill — Publish a skill

Advertised by the server during the last successful anonymous check.

Publish a runx skill so others can find and install it.

No arguments advertised.

wrap_mcp_server — Wrap an MCP server

Advertised by the server during the last successful anonymous check.

Turn an existing MCP server into a governed runx skill.

No arguments advertised.

Resources

0 advertised

runx skill

Advertised by the server during the last successful anonymous check.

The published manifest for one runx skill, addressed by its publisher/name id.

runx skill URI template
runx://skills/{skill_id}

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 (1 of 1 answered).

  1. 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
868 ms
95th percentile latency
868 ms

Maintenance history

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

  • · probe · passed · 868 ms · metadata changed · 2 tool(s), 0 resource(s), 1 resource template(s), 4 prompt(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 runx-mcp https://api.runx.ai/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 runx-mcp --url https://api.runx.ai/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable runx-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "runx-mcp": {
      "url": "https://api.runx.ai/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "runx-mcp": {
      "type": "streamableHttp",
      "url": "https://api.runx.ai/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start runx-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "runx-mcp": {
      "type": "http",
      "url": "https://api.runx.ai/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 runx-mcp https://api.runx.ai/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://api.runx.ai/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": {
    "runx-mcp": {
      "serverUrl": "https://api.runx.ai/mcp"
    }
  }
}

Let your agent find its tools

Find servers like runx 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
See all 8,851

Do you run runx MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing