Local codebase intelligence CLI and MCP server that gives Claude a SQLite code graph, change-safety gates, code health checks, impact analysis, review tools, and audit evidence for agent-assisted coding.
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.
Author
Cranot
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-06
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
63
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Needs review
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
No reviewed flag detected in metadata.
Pending
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
5 safety and 4 privacy notes across 5 risk areas. Review closely: credentials & tokens.
5 areas
SafetyGeneralRoam Code exposes many code-intelligence MCP tools; choose the narrowest `ROAM_MCP_PRESET` needed for the workflow.
SafetyLocal filesThe server indexes local source code into a `.roam` SQLite-backed graph and may write run ledgers, decision receipts, caches, and generated evidence files.
SafetyGeneralSome workflows can support change planning, review, and higher-authority modes, so keep `ROAM_AGENT_MODE` aligned with the MCP client's approval model.
SafetyExecution & processesStatic analysis, blast-radius, security, and health checks can miss runtime behavior or project-specific constraints.
SafetyGeneralTreat Roam Code output as guidance for review and testing, not as proof that a change is safe to merge.
PrivacyLocal filesLocal source paths, symbols, imports, call graphs, git history, dependency relationships, and run evidence can be written to local Roam Code artifacts.
PrivacyCredentials & tokensThe README describes the project as local by default with no API keys required and opt-in summary-only metrics push as the outbound surface.
PrivacyData retentionReview `.roam` artifacts, generated evidence, SARIF, reports, and logs before sharing them outside the repository.
PrivacyGeneralAvoid indexing private, regulated, or customer code unless the local machine, MCP client, and model workflow are approved for that codebase.
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.
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.
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:
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.
Local codebase intelligence CLI and MCP server that gives Claude a SQLite code graph, change-safety gates, code health checks, impact analysis, review tools, and audit evidence for agent-assisted coding.
Local-first codebase intelligence MCP server that indexes repositories with tree-sitter, stores searchable chunks in DuckDB, and gives Claude semantic search, regex search, daemon status, and deep code research tools.
High-performance MCP server that indexes codebases into a persistent knowledge graph for structural search, call tracing, architecture summaries, dead-code detection, and cross-repo analysis.
Code intelligence MCP server with a Zig core for local project indexing, structural outlines, symbol lookup, search, dependency graphs, snapshots, remote public-repo queries, and fallback edits.
✓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.
✓ChunkHound reads source files, Markdown, text, PDFs, and supported config files under the target directory and stores indexed chunks in a local database.
Realtime indexing and daemon mode can continue watching project files after the initial MCP connection.
Code research and web search tools require embedding, reranking, and LLM configuration and may invoke local CLIs or external model APIs depending on settings.
Exclude generated files, vendored dependencies, secrets, large artifacts, and unrelated repositories before indexing broad workspace roots.
Review MCP client configuration carefully when using an absolute project path in a global Claude Desktop config.
✓Codebase Memory MCP reads source files across indexed repositories and writes MCP entries, instruction files, skills, hooks, and agent configuration files during install.
The background watcher and auto-index features can keep graph data updated as source files change.
The optional graph UI exposes a local visualization server on a localhost port.
Shared graph artifacts and SQLite databases can persist source metadata after an MCP session ends.
Verify downloaded release binaries, checksums, signatures, and provenance before running them in sensitive environments.
✓CodeDB indexes local projects and exposes file tree, outline, search, symbol, caller, dependency, read, snapshot, project, and context tools to the MCP client.
CodeDB's `codedb_edit` tool exists as a fallback editing tool and can create, replace, insert, delete, or modify files when used by a client without native edit tooling.
The npm package runs a postinstall step that downloads a native binary from GitHub Releases; review package and release provenance in environments that restrict native binaries.
Remote repo queries use the public `api.wiki.codes` service and should be treated as network access outside the local repository.
The upstream README marks the project as alpha software, with parser coverage and snapshot formats still stabilizing.
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.
✓Indexed chunks, file paths, symbols, comments, Markdown, PDFs, configuration values, database files, daemon state, and search results can reveal proprietary source code and internal architecture.
Embedding, reranking, LLM, and web search providers may receive code-derived queries or snippets if configured.
Local ChunkHound database files, logs, daemon state, and MCP transcripts may retain code-derived context after the session ends.
Avoid sharing ChunkHound databases, config files with API keys, verbose logs, research outputs, and screenshots from private repositories.
✓Source code, filenames, paths, symbols, comments, imports, routes, call graphs, architecture summaries, ADRs, graph queries, prompts, and tool outputs may be visible to the MCP client and model provider.
Persistent graph databases and shared artifacts can retain proprietary architecture, internal package names, route names, service boundaries, and accidentally committed secrets.
Auto-indexing broad workspace roots can include unrelated private repositories or generated files.
Avoid committing shared graph artifacts unless the repository owners explicitly approve storing derived code intelligence in version control.
✓Local indexes, snapshots, file trees, symbol names, dependency graphs, snippets, read results, and search results can reveal proprietary code structure and implementation details.
Upstream documents sensitive-file blocking for patterns such as environment files, credentials, and keys, but users should still review ignore rules and avoid indexing secret-heavy directories.
CodeDB writes telemetry to `~/.codedb/telemetry.ndjson` unless `CODEDB_NO_TELEMETRY=1` is set, then syncs aggregate tool counts, latency, startup, file count, line count, language, version, and platform data on MCP session close.
Upstream telemetry docs state that source code, file contents, file paths, and search queries are not collected.
Remote public-repo queries and local MCP responses may still be logged by MCP clients, model providers, and terminal history.
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.
Python 3.10 or newer and the `uv` package manager.
A local repository or workspace you are authorized to index.
ChunkHound JSON config reviewed for database path, excludes, embeddings, and LLM provider settings.
Optional embedding provider credentials for semantic search, or regex-only usage when no embedding key is configured.
A local repository or workspace you are authorized to index.
Platform-compatible Codebase Memory MCP release binary verified before use.
Agent configuration write access reviewed before running the installer.
Sensitive paths, generated files, vendored code, secrets, and private repositories reviewed before indexing.
macOS or Linux on x64 or arm64 for the published native binary launcher.
Node.js 18 or newer when using the `codedeebee` npm launcher.
A local project directory that the MCP client exposes through roots or launches from.
Review of which local repositories, file types, generated artifacts, and secrets patterns may be indexed.