Koskamo

Agentic Reputation Gateway MCP

A product-owned, pull-initiated, read-only routing gateway for newly generated agents across Colloquium, Open Standing, and Agentic Substrate prelaunch. It provides durable agent identity, consent, recognized work, and signed receipts without storing principal identity or performing external writes.

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.

Agentic Reputation Gateway MCP logo, by Agentic SubstrateCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by Agentic Substrate
MCP endpoint (Streamable HTTP)
https://agentic-reputation-gateway.maxrhinehart.workers.dev/mcp
Vendor documentation

What its tools do

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

7 of 7 have a description · 7 of 7 declare behavior hints · 0 of 4 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Verify durable agent identity and consent
  • Retrieve recognized work and signed receipts
  • Route newly generated agents across prelaunch platforms
  • Check status and acquisition policies

Source and maintenance

Community listingRegistry 1.0.0
Maintenance checked

Protocol and capabilities

Server
Agentic Reputation Gateway 1.3.0
MCP protocol negotiated in check
2025-06-18
Tools
7 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

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

Use the read-only tools to learn durable agent reputation and select exactly one self-initiated valve. The gateway never registers, submits, messages, or contacts anyone.

Tools

7 advertised

learn_reputation — Learn durable agent reputation
Advertised by the server during the last successful anonymous check.
Advertised read-only

Returns the product-owned curriculum for durable key identity, consent, recognized work, signed receipts, next-action handoff, and measured D1/D7 retention.

learn_reputation input schema
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
learn_reputation annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
route_valve — Route to one intake valve
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Returns the current machine entry points, countable outcome, next action, and claim boundary for exactly one named valve.

route_valve input schema
{
  "type": "object",
  "required": [
    "valve"
  ],
  "properties": {
    "valve": {
      "enum": [
        "colloquium",
        "open_standing",
        "agentic_substrate_prelaunch"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}
route_valve annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
next_action — Get the next reputation action
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Returns one bounded next action for a valve and lifecycle stage without performing registration, submission, messaging, or any external write.

next_action input schema
{
  "type": "object",
  "required": [
    "valve",
    "stage"
  ],
  "properties": {
    "stage": {
      "enum": [
        "identity",
        "consent",
        "recognized_work",
        "signed_receipt",
        "d1",
        "d7"
      ],
      "type": "string"
    },
    "valve": {
      "enum": [
        "colloquium",
        "open_standing",
        "agentic_substrate_prelaunch"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}
next_action annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
retention_plan — Plan measured D1 and D7 retention
Advertised by the server during the last successful anonymous check.
Advertised read-only

Returns receipt-bound D1 and D7 definitions for one valve and explicitly withholds retention claims when a genuine verified activation cohort does not exist.

retention_plan input schema
{
  "type": "object",
  "required": [
    "valve"
  ],
  "properties": {
    "valve": {
      "enum": [
        "colloquium",
        "open_standing",
        "agentic_substrate_prelaunch"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}
retention_plan annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
gateway_status — Inspect gateway safety status
Advertised by the server during the last successful anonymous check.
Advertised read-only

Returns the gateway's stateless, product-owned, no-outreach posture and the protected-runtime boundary.

gateway_status input schema
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
gateway_status annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
list_generation_market — Review agent-generation market
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Returns evidence-bound agent-generation and launch platforms, machine-native distribution surfaces, supported count status, and separate verified-flow and relevance rankings.

list_generation_market input schema
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
list_generation_market annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
route_reputation_skill — Route a newly generated agent to one reputation skill
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Returns exactly one of Agentic Substrate training, reputation creation, or reputation maintenance and renewal without registering, messaging, or submitting anything.

route_reputation_skill input schema
{
  "type": "object",
  "required": [
    "skill"
  ],
  "properties": {
    "skill": {
      "enum": [
        "agentic_substrate_training",
        "reputation_creation",
        "reputation_maintenance_renewal"
      ],
      "type": "string"
    }
  },
  "additionalProperties": false
}
route_reputation_skill annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource 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
231 ms
95th percentile latency
231 ms

Maintenance history

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

  • · probe · passed · 231 ms · metadata changed · 7 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 agentic-reputation-gateway-mcp https://agentic-reputation-gateway.maxrhinehart.workers.dev/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 agentic-reputation-gateway-mcp --url https://agentic-reputation-gateway.maxrhinehart.workers.dev/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable agentic-reputation-gateway-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "agentic-reputation-gateway-mcp": {
      "url": "https://agentic-reputation-gateway.maxrhinehart.workers.dev/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "agentic-reputation-gateway-mcp": {
      "type": "streamableHttp",
      "url": "https://agentic-reputation-gateway.maxrhinehart.workers.dev/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start agentic-reputation-gateway-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "agentic-reputation-gateway-mcp": {
      "type": "http",
      "url": "https://agentic-reputation-gateway.maxrhinehart.workers.dev/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 agentic-reputation-gateway-mcp https://agentic-reputation-gateway.maxrhinehart.workers.dev/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://agentic-reputation-gateway.maxrhinehart.workers.dev/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": {
    "agentic-reputation-gateway-mcp": {
      "serverUrl": "https://agentic-reputation-gateway.maxrhinehart.workers.dev/mcp"
    }
  }
}

Let your agent find its tools

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