Roam Code MCP Server for Claude

Safety notes

Roam Code exposes many code-intelligence MCP tools; choose the narrowest `ROAM_MCP_PRESET` needed for the workflow.
The server indexes local source code into a `.roam` SQLite-backed graph and may write run ledgers, decision receipts, caches, and generated evidence files.
Some workflows can support change planning, review, and higher-authority modes, so keep `ROAM_AGENT_MODE` aligned with the MCP client's approval model.
Static analysis, blast-radius, security, and health checks can miss runtime behavior or project-specific constraints.
Treat Roam Code output as guidance for review and testing, not as proof that a change is safe to merge.

Privacy notes

Local source paths, symbols, imports, call graphs, git history, dependency relationships, and run evidence can be written to local Roam Code artifacts.
The README describes the project as local by default with no API keys required and opt-in summary-only metrics push as the outbound surface.
Review `.roam` artifacts, generated evidence, SARIF, reports, and logs before sharing them outside the repository.
Avoid indexing private, regulated, or customer code unless the local machine, MCP client, and model workflow are approved for that codebase.

Prerequisites

Python 3.10 or newer.
A local repository that can be indexed by Roam Code.
Permission for the MCP client to read the target codebase and write Roam Code local index and evidence artifacts.
Run `roam init` or `roam index` in the repository before expecting complete graph-aware answers.

Schema details

Install type: cli
Troubleshooting: No

Source repository stats

Scope: Source repo

Collection metadata

Estimated setup: 20 minutes
Difficulty: intermediate

Tool listing metadata

Website: https://roam-code.com/

Full copyable content

{
  "mcpServers": {
    "roam-code": {
      "command": "roam",
      "args": ["mcp"],
      "env": {
        "ROAM_MCP_PRESET": "core"
      }
    }
  }
}

About this resource

Content

Roam Code is a local-first codebase intelligence CLI and Model Context Protocol server for AI coding agents. It builds a SQLite-backed graph of a repository so Claude can ask for focused code context, pre-change safety checks, impact analysis, health signals, retrieval, review evidence, and audit-oriented metadata without relying on a cloud account.

The default MCP preset exposes the core tool surface for common coding-agent workflows. Additional presets are documented upstream for review, refactor, debugging, architecture, compliance, and full-tool scenarios.

Source Review

These sources were reviewed on 2026-06-06. Prefer the live repository, README, PyPI metadata, package metadata, MCP server manifest, MCP server source, and license file for current install commands, presets, tool counts, local-first behavior, write surfaces, and licensing.

Features

Python package roam-code with optional MCP extra.
Stdio MCP server launched with roam mcp.
Local SQLite code graph built from an indexed repository.
Core MCP preset for context, retrieval, preflight, impact, diff, PR risk, affected tests, health, diagnostics, critique, and related coding-agent tasks.
Optional presets for review, refactor, debug, architecture, compliance, and full tool exposure.
Local run ledgers, decision receipts, and ChangeEvidence-style audit artifacts documented in the repository.
MCP mode and receipt controls documented for read-only and higher-authority agent workflows.
Apache-2.0 license.

Installation

Install Roam Code with the MCP extra, index a repository, then configure the stdio MCP server:

pip install "roam-code[mcp]"
roam init

{
  "mcpServers": {
    "roam-code": {
      "command": "roam",
      "args": ["mcp"],
      "env": {
        "ROAM_MCP_PRESET": "core"
      }
    }
  }
}

After restarting the MCP client, ask Claude to use Roam Code for context, preflight, impact, or review checks before changing an indexed repository.

Use Cases

Ask for graph-aware context before editing a symbol.
Run preflight checks before a refactor.
Estimate blast radius and affected tests for a planned change.
Review an uncommitted diff against local code graph facts.
Query health, complexity, dependencies, cycles, and code smells.
Retrieve task-specific files and symbols without repeated raw search.
Produce local audit evidence for agent-assisted code changes.

Safety and Privacy

Roam Code is powerful because it has local codebase visibility. It can read and index source files, derive graph facts, inspect git history, and write local artifacts under Roam Code-managed paths. Keep the MCP preset and agent mode as narrow as the workflow allows, and verify Roam Code findings with tests and human review before merging changes.

The README describes Roam Code as local by default with no API keys required. Even so, indexed code facts, generated reports, run ledgers, receipts, SARIF, and evidence bundles may contain sensitive repository details. Review those artifacts before sharing them, and avoid indexing private or regulated code in unapproved model workflows.

Duplicate Check

Existing MCP content includes code search, code review, repository, and developer-tool servers, but no dedicated entry for Cranot/roam-code or the roam-code PyPI package was found in content/mcp. This entry is distinct because it covers a local code graph and MCP server for preflight, retrieval, impact analysis, review evidence, and agent coding safety workflows.

#codebase-intelligence#code-review#local-first#static-analysis#agents