# @neurcode-ai/mcp-server

Source: https://glimind.com/server/npm%2F-neurcode-ai%2Fmcp-server
Registry id: `npm/-neurcode-ai/mcp-server`
Status: unknown

## Install

```json
{
  "mcpServers": {
    "neurcode-ai-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@neurcode-ai/mcp-server"
      ]
    }
  }
}
```

Claude Code:

```sh
claude mcp add neurcode-ai-mcp-server -- npx -y @neurcode-ai/mcp-server
```

## Tools (28)

- `neurcode_agent_edit_before`: Check a proposed file write before the MCP agent edits it.
- `neurcode_agent_plan_amend`: Re-plan when scope changes during implementation.
- `neurcode_agent_plan_capture`: Capture the agent's source-free implementation plan before edits.
- `neurcode_agent_session_finish`: Finish the governed session and write replayable evidence.
- `neurcode_agent_session_handshake`: Handshake an MCP-capable agent into a launcher-created governed session.
- `neurcode_agent_session_status`: Inspect the active governed session and next required agent action.
- `neurcode_contract_import`: Import an external plan (Claude/Cursor/Codex) into a Neurcode contract.
- `neurcode_feedback_list`: List submitted feedback for a verification ID.
- `neurcode_feedback_review`: Admin review (approve/reject) for submitted feedback.
- `neurcode_feedback_stats`: Aggregate feedback quality stats.
- `neurcode_feedback_submit`: Submit false-positive / false-negative feedback.
- `neurcode_governance_loop`: verify → remediate-on-fail → re-verify in a single MCP call.
- `neurcode_plan`: Generate an execution plan from a natural-language intent.
- `neurcode_prompt`: Render a Cursor/Claude prompt from an existing plan.
- `neurcode_remediate`: Run the controlled remediation ship loop and re-verify.
- `neurcode_runtime_adapter_capabilities`: List available runtime adapters and whether they hard-deny, cooperate, observe, or run as a post-change backstop.
- `neurcode_runtime_event`: Submit a normalized source-free agent lifecycle event such as session.start, plan.capture, or edit.before.
- `neurcode_runtime_guard`: Pre-generation deterministic enforcement (start/check/status/stop).
- `neurcode_session_amend_plan`: Amend the current source-free agent plan as implementation understanding evolves.
- `neurcode_session_approve`: Apply an exact-path approval to the current governed session.
- `neurcode_session_obligations`: Inspect live source-free architecture obligations.
- `neurcode_session_waive_obligation`: Record a human-authorized obligation waiver with bounded expiry.
- `neurcode_ship`: End-to-end ship workflow (plan → apply → verify → publish).
- `neurcode_ship_attestation_verify`: Verify a release attestation JSON document.
- `neurcode_ship_resume`: Resume a persisted ship run by ID.
- `neurcode_ship_runs`: List persisted ship runs for the current repository.
- `neurcode_simulate`: Predict blast radius and regressions before merge.
- `neurcode_verify`: Run deterministic governance verification against a plan, with optional policy-only mode.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.