Koskamo

review-mcp

A remote MCP server that provides adversarial multi-model code review for AI coding agents. It routes code through a panel of different models plus deterministic detectors to return a structured pass/fail verdict with typed issues and suggested fixes.

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.

review-mcp logo, by HectorGuerillaCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-06Published by HectorGuerilla
MCP endpoint (Streamable HTTP)
https://review-mcp-production.up.railway.app/mcp
Vendor documentation

What its tools do

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

Not annotated (1)

1 of 1 have a description · 0 of 1 declare behavior hints · 1 of 1 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

  • Review code before shipping or merging a change
  • Get a second opinion on a risky diff
  • Act as a quality gate inside an autonomous build loop
  • Review code when a single-model agent would miss its own blind spots

Source and maintenance

Community listingRegistry 0.1.0

Protocol and capabilities

Server
review-mcp 0.1.0
MCP protocol negotiated in check
2025-11-25
Tools
1 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Tools

1 advertised

review_code
Advertised by the server during the last successful anonymous check.

Adversarial multi-model code review. Submit a diff, a module, or a spec+implementation and get back a structured pass/fail verdict with each issue's type, severity, location, explanation, and suggested fix. Why call this instead of reviewing your own output: a single model shares its blind spots with itself. This routes your code through a panel of *different* models plus a set of deterministic detectors, catching what self-review misses — path/contract violations, module incoherence (dangling imports, broken cross-references), syntax and call-arity regressions in a diff's post-image, and 'prose instead of tool calls' (output that describes an action rather than emitting it). The panel adds semantic judgment on top and never overrides a deterministic finding. Call it before shipping or merging, as a second opinion on a risky change, or as a gate in an autonomous build loop. Choose depth='fast' (one model, low latency) or 'deep' (full panel, higher recall). Deep review audits files of any size in milestone chunks so every panel model contributes; the price (shown in the 402) and the payment window scale with file size. Per-call limit ~1,600 lines — larger inputs return 413, so split by file/module and call once per file. Paid per call via x402 (USDC on Base); the price is announced in the 402 response before any charge.

review_code input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "payload",
    "language"
  ],
  "properties": {
    "depth": {
      "enum": [
        "fast",
        "deep"
      ],
      "type": "string",
      "description": "\"fast\" = single-model, low latency; \"deep\" = full panel, higher recall (default \"deep\")."
    },
    "context": {
      "type": "string",
      "description": "optional spec/intent, related interfaces, constraints, or what the change should do."
    },
    "payload": {
      "type": "string",
      "description": "a unified diff, a complete module/file, or a spec plus its implementation (include enough context lines for diffs)."
    },
    "language": {
      "type": "string",
      "description": "primary language of the payload (e.g. \"typescript\", \"python\")."
    }
  },
  "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).

  1. 2026-11-06: 1 of 1 checks answered
  2. 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
889 ms
95th percentile latency
889 ms

Maintenance history

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

  • · probe · passed · 889 ms · metadata changed · 1 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 review-mcp https://review-mcp-production.up.railway.app/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 review-mcp --url https://review-mcp-production.up.railway.app/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable review-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "review-mcp": {
      "url": "https://review-mcp-production.up.railway.app/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "review-mcp": {
      "type": "streamableHttp",
      "url": "https://review-mcp-production.up.railway.app/mcp",
      "disabled": false
    }
  }
}

VS Code

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

Let your agent find its tools

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