Lets AI coding agents inspect repository structure, search code, and recall project conventions via MCP and CLI.
Also known as PatrickSys/codebase-context
- Stars
- 68
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 7, 2026
- License
- —
What is Codebase Context MCP?
Codebase Context lets AI coding agents inspect repository structure, search code, and recall project conventions via MCP and CLI.
Summary generated from the project's README
About Codebase Context MCP server
Helping AI coding agents understand complex repositories is what codebase-context enables through specialized indexing and retrieval tools. Developers use this tool to provide agents with a high-level repository map, symbol references, and file relationships, allowing an AI to inspect a project structure before attempting any edits. It works locally via stdio or through an advanced HTTP setup, and it can be initialized for specific clients like Claude Code, Cursor, Codex, and OpenCode.
Users can choose between a default keyword-based index that requires no API keys or GPU, or an optional semantic indexing mode that uses embedding providers. The system includes unique features like project memory to store conventions and a review context tool that creates a bounded packet from Git diffs. While the keyword index is limited to 5,000 searchable chunks by default, users can adjust these limits through configuration. It provides specific analyzers for frameworks such as React, Next.js, Angular, and NestJS to improve how agents navigate codebases.
What you can do with it
- 1Map repository structureAsk an AI agent to generate a high-level overview of the project organization and patterns before starting a task.
- 2Search for specific codeDirect an AI to find specific symbols or features within the codebase using ranked search results.
- 3Recall project conventionsInstruct an agent to retrieve previously stored decisions or architectural rules using the memory tools.
- 4Analyze recent changesProvide an AI with the necessary context from a recent commit to perform a focused code review.
Written from the project's README. Every use case is checked against a quote from it.
How to install Codebase Context MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Codebase Context MCP in Claude Code
$ claude mcp add codebase-context -- npx -y codebase-contextInstall Codebase Context MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"codebase-context": {
"command": "npx",
"args": [
"-y",
"codebase-context"
]
}
}
}Install Codebase Context MCP in VS Code
.vscode/mcp.json
{
"servers": {
"codebase-context": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"codebase-context"
]
}
}
}Install Codebase Context MCP in VS Code CLI
$ code --add-mcp '{"name":"codebase-context","type":"stdio","command":"npx","args":["-y","codebase-context"]}'Install Codebase Context MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"codebase-context": {
"command": "npx",
"args": [
"-y",
"codebase-context"
]
}
}
}Install Codebase Context MCP in Codex
$ codex mcp add codebase-context -- npx -y codebase-contextInstall Codebase Context MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.codebase-context] command = "npx" args = ["-y", "codebase-context"]
Install Codebase Context MCP in Gemini CLI
$ gemini mcp add -s user codebase-context npx -- -y codebase-contextInstall Codebase Context MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"codebase-context": {
"command": "npx",
"args": [
"-y",
"codebase-context"
]
}
}
}Automated checks
Ran Nov 13, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work · What to fix for more points
- Source repository linked and reachablepatricksys/codebase-context is public and reachablegithub.com/patricksys/codebase-context ↗Pass
- Package names this repository as its sourcecodebase-context names patricksys/codebase-context as sourcenpmjs.com/package/codebase-context ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for codebase-contextnpmjs.com/package/codebase-context/v/2.2.0#provenance ↗Pass
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-11-07github.com/patricksys/codebase-context ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from codebase-contextPass
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubCodebase Context
Local repository maps, code search and symbol references for coding agents. Codebase Context exposes these through MCP and a CLI so an agent can inspect the repository before editing it.
Published beta: 2.3.1-beta.0 (stable: 2.2.0)
As checked on 4 November 2026, npm beta points to 2.3.1-beta.0, while npm latest remains 2.2.0. The beta requires Node.js 22 or newer. An unpinned npx -y codebase-context may use an already installed local version; without one, it resolves npm latest (currently the stable 2.2.0). To select the published beta explicitly, use npx -y codebase-context@2.3.1-beta.0 --version. A source checkout or a local tarball is separate from a verified registry release.
Fresh beta indexes use keyword search without downloading an embedding or reranker model. Existing indexes keep their recorded mode. Semantic indexing is an explicit option; its optional runtimes and model downloads are separate from the default path.
Try the beta or a local build from the terminal
Use an explicitly installed 2.3.1-beta.0, a built checkout (pnpm install, then pnpm build in the CBC checkout) or an installed local tarball. From the repository you want to inspect, point Node at that installation's actual entrypoint:
node /path/to/codebase-context/dist/index.js --version
node /path/to/codebase-context/dist/index.js map
node /path/to/codebase-context/dist/index.js search --query "a symbol or feature in this repository" --limit 5
node /path/to/codebase-context/dist/index.js status
Replace the paths and query with your own. For a tarball installed under /path/to/cbc-local, the entrypoint is /path/to/cbc-local/node_modules/codebase-context/dist/index.js. Quote paths containing spaces.
map builds an index when the folder has no previous index. It then returns a bounded repository map. Search returns ranked source locations; open the returned code before relying on it. Low confidence means weak matching evidence, not that an implementation is absent.
To refresh the index, use reindex. Omitting mode flags preserves the recorded mode; reindex --no-embeddings explicitly selects keyword-only indexing. reindex --embeddings selects the configured embedding provider and requires optional LanceDB storage. The default local provider also requires Transformers and may download models; an explicitly configured remote provider has its own connection requirements. Changing modes requires a full rebuild, including when --incremental is supplied.
Set up your AI client
From the target repository, the installed beta or built source can write project registrations for selected detected clients:
node /path/to/codebase-context/dist/index.js init
# Or select one client explicitly:
node /path/to/codebase-context/dist/index.js init --client codex --root /path/to/project --yes
The wizard recognizes Claude Code, Codex, Cursor and OpenCode. It saves the Node binary and package entrypoint that ran setup. If that installation or its npx cache is moved or removed, rerun setup. Writing a config does not prove that a native client connected or completed a coding task.
After registration, restart the client and ask:
Use Codebase Context to find [feature] in this repository. Pass this repository's absolute path as project, wait for indexing if needed, and open the relevant source files.
The client setup guide contains beta setup instructions and dated checks for the older stable package. Historical manual recipes, including Windsurf, retain their dated verification limits. For example, the following manual registration leaves the package version unpinned; it may use an already installed local version or fall back to npm latest, so it does not reliably select the beta:
claude mcp add --scope user --transport stdio codebase-context -- npx -y codebase-context
The default transport is stdio: the client starts the server. HTTP is an advanced option with client-specific setup. Explicit project selection is the portable default. A successful selection becomes active for later calls in that server process; select again after restarting or changing repositories.
What your agent can inspect
- Repository map: structure, detected patterns and example files before narrowing to a task.
- Code search: bounded, ranked results with source locations and search-quality information. The default compact response contains at most six results.
- Symbol references: static identifier occurrences. They are not a runtime call graph.
- File relationships: TypeScript/JavaScript imports and re-exports, with unresolved or stale edges reported. Python and Go import navigation are not supported.
- Team patterns: file-level frequencies and example files. These are observations about the repository, not prescriptions about code quality.
- Project memory:
rememberandget_memorystore and retrieve project conventions, decisions, gotchas and failures. - Review context:
codebase-context-reviewbuilds a bounded packet from a committed Git diff. It does not review code or establish reviewer quality. The review-context guide retains a separate historical version preview; it is not evidence of this candidate's publication.
Dedicated analyzers in the source cover Angular, React, Next.js and NestJS. Other files use the generic analyzer and available parsers. See the capabilities reference for scope and limitations.
Privacy and storage
The default keyword index is built locally. Docker, a GPU and an API key are not required. Optional local embeddings also run on the machine. If you explicitly configure a remote embedding provider, code chunks are sent to that provider.
Your AI client may send returned code to its own model provider; CBC does not control that connection. Project memory also travels with the repository if you commit and push it.
Generated index data should stay out of version control. To share project memory while ignoring the generated index:
.codebase-context/*
!.codebase-context/memory.json
Evidence and limits
The benchmark report and prior report archive describe separate historical experiments. These are retrieval observations, not a winner or a coding-quality claim. This historical evidence does not establish patch correctness or end-to-end coding quality. Versions, fixtures and failure records matter; these reports do not certify this candidate. This draft makes no claim that CBC beats text search, improves coding outcomes, or reduces time or tokens.
The default keyword path can miss natural-language questions when their vocabulary differs from the code. A returned file and a high score are not proof that an answer is correct. Inspect the cited implementation. Optional semantic search has not established a retrieval-quality advantage for this candidate.
Other practical limits:
- The default keyword index holds at most 5,000 searchable chunks per project.
projects[].parsing.maxChunkscan raise that limit. - Search has bounded candidate inspection. Narrow a query when the candidate budget is exhausted; refresh when source files changed or became unavailable.
- Existing formats or incomplete generations can require an explicit rebuild or recovery choice. A failed operation is not a successful recovery.
- Setup evidence differs by client. Config writing, protocol connectivity and native-client task completion are separate checks.
- Stdio routing checks do not establish concurrent HTTP client isolation.
Reference
- Client setup — candidate registration, dated checks and limits
- Capabilities — tools, routing, configuration and optional modes
- CLI — local-candidate commands and historical illustrations
- Benchmark — historical methods, observations and failures
- Contributing — local development and evaluation commands
- Changelog — candidate changes and historical entries
Elastic-2.0. See LICENSE.
Codebase Context MCP questions
How do I add Codebase Context MCP to Claude Code?
Run claude mcp add codebase-context -- npx -y codebase-context in your terminal. Add --scope user to make it available in every project.
How do I add Codebase Context MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What can an AI agent inspect with Codebase Context?
The agent can view a repository map, run ranked code search, look up symbol references and file relationships, observe team patterns, and store or retrieve project memory.
Does Codebase Context require Docker, a GPU, or an API key?
No. The default keyword index builds locally without Docker, a GPU, or an API key. Optional embeddings also run locally unless you explicitly configure a remote provider.
Which AI clients can Codebase Context set up automatically?
The init wizard recognizes Claude Code, Codex, Cursor and OpenCode and writes project registrations for them.
How many results does a default code search return?
The default compact search response contains at most six ranked results.
Should generated index data be committed to version control?
No. You should keep generated index data out of version control and can optionally commit only the project memory file.