Koskamo

Objective Trust MCP

A remote MCP server that ranks other MCP endpoints by health and user outcomes before payment. It allows agents to set objectives, record outcomes, and rank tools for specific tasks using a score derived from health, probe age, and quoted USD, excluding sponsored results.

Endpoint and access

API key: create a key with the vendor first; your client sends it as an authorization header on every request.

Objective Trust MCP logo, by AgentShareCommunity listingStreamable HTTPAPI keyEndpoint checked 2026-11-01Published by AgentShare
You need:dual-auth (API key or x402)
MCP endpoint (Streamable HTTP)
https://agentshare.dev/mcp/objective-trust
Vendor documentation

What you can do with it

  • Rank MCP tools for a specific task
  • Set objectives for MCP evaluation
  • Record outcomes of MCP usage
  • Check health status of MCP endpoints

Source and maintenance

Community listingRegistry 1.0.0
Maintenance checked

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

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
523 ms
95th percentile latency
523 ms

Maintenance history

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

  • · probe · passed · 523 ms · metadata changed · refuses unauthenticated initialize (HTTP 401)

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 objective-trust-mcp https://agentshare.dev/mcp/objective-trust

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 objective-trust-mcp --url https://agentshare.dev/mcp/objective-trust

Cursor

Merge this server into .cursor/mcp.json in your project, then enable objective-trust-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "objective-trust-mcp": {
      "url": "https://agentshare.dev/mcp/objective-trust"
    }
  }
}

Cline

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

VS Code

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

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 objective-trust-mcp https://agentshare.dev/mcp/objective-trust

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "objective-trust-mcp": {
      "url": "https://agentshare.dev/mcp/objective-trust"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "objective-trust-mcp": {
      "serverUrl": "https://agentshare.dev/mcp/objective-trust"
    }
  }
}

Let your agent find its tools

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