Enigmagent MCP Server

Your AI agent types `{{GITHUB_TOKEN}}`. The placeholder leaves the model and travels through the conversation, the logs, the context window — and

Local serverstdioPython

What is the Enigmagent MCP server?

Your AI agent types {{GITHUB_TOKEN}}. The placeholder leaves the model and travels through the conversation, the logs, the context window — and only at the moment your tool actually needs the credential does EnigmAgent intercept the. Exposed over MCP by the enigmagent mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

Its toolset

Everything the assistant can do here goes through one of these:

  • name — enigmagent
  • Side — channels (timing, swap, core dumps) — out of scope for v0.x
  • Syntax — Resolves to
  • Layer — Implementation
  • Approach — Secret in prompt?
  • EnigmAgent — ✅ No
  • Component — Role
  • OpenCLAW-P2P — Core protocol · Lean 4 proofs · Papers
  • BenchClaw — 17-judge agent benchmarking
  • AgentBoot — Bare-metal OS installer
  • CAJAL — 4B research LLM for papers
  • Cursor — The Cursor tool exposed by this server

Adding it to your client

enigmagent-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Configuration

You will need one environment variable: GITHUB_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

When to reach for it

Plenty of monitoring and observability servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Enigmagent's toolset — name, Side, Syntax and 9 more — is a fair guide to whether it matches your workflow. It is maintained by agnuxo1; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 12 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Enigmagent.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the enigmagent mcp server does with a few real requests.

Available tools

ToolWhat it does
nameenigmagent
Sidechannels (timing, swap, core dumps) — out of scope for v0.x
SyntaxResolves to
LayerImplementation
ApproachSecret in prompt?
EnigmAgent✅ **No**
ComponentRole
OpenCLAW-P2PCore protocol · Lean 4 proofs · Papers
BenchClaw17-judge agent benchmarking
AgentBootBare-metal OS installer
CAJAL4B research LLM for papers
CursorThe Cursor tool exposed by this server.

How to install the Enigmagent MCP server

{
  "mcpServers": {
    "enigmagent": {
      "command": "npx",
      "args": ["-y", "enigmagent-mcp"],
      "env": {
        "GITHUB_TOKEN": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
GITHUB_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use Enigmagent to name.
  • Use Enigmagent to Side.
  • Use Enigmagent to Syntax.

Frequently asked questions

It connects Enigmagent to MCP-compatible AI assistants such as Claude and Cursor, exposing 12 tools (name, Side, Syntax, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Enigmagent directly.