Indexes TypeScript services across a GitHub organization, enabling cross-repo, type-aware, intent-aware queries about endpoints, types, and function behavior through MCP tools.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Carrick which functions handle webhook signing across our services?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Coding agents working across full-stack and multi-service codebases routinely rebuild existing helpers, trust stale type definitions, and modify API contracts without knowing who consumes them.
Carrick solves this by indexing your entire TypeScript ecosystem, from frontend apps to backend services, whether they live in a monorepo or across multiple repositories. By integrating deeply with the TypeScript compiler, Carrick traces every route, type, and cross-service call while recording function behaviour—so agents search by intent rather than name and stay grounded in your real architecture.
Delivered via MCP for AI agents and LSP for IDEs, Carrick ensures models see existing endpoints and utilities before generating new code. The scanner is source-available, runs from your CLI or CI pipeline, and includes a Free plan so you can start building safer agent workflows immediately.
npm install -g carrick
carrick initcarrick init signs you in, asks which repositories to index and connects your agent. Your agent then writes each repository's carrick.json and runs the first scan. The quick start has the details (Node 24 or newer).
Related MCP server: MCP Indexer
Search existing code through your agent, inspect live contracts in your editor, and catch breaking changes in your pull requests.
Give your AI assistants complete context on what already exists, how endpoints are shaped, and who breaks if something changes. Carrick maps every function by what it actually does, allowing agents to find existing implementations and build on them—even in repositories you haven't checked out locally. Endpoint types are pulled straight from the TypeScript compiler in the service that exposes them.
Works with any MCP-compatible agent, including Claude Code, Cursor, Windsurf, and Codex.
Inspect cross-service contracts and jump between connected files without leaving your IDE. "Go to Definition" jumps directly from a service call to its handler when the code is on disk, while Code Lens displays every caller across your local index inline. If a frontend call and backend handler fall out of sync, Carrick surfaces type mismatches as native editor diagnostics.
Available on the Visual Studio Marketplace and Open VSX, or runnable as a standard LSP server.
Bring the exact same index into CI to catch contract risks, duplicate work, and silent version drift. When a producer and consumer fall out of sync—regardless of protocol—Carrick flags the exact mismatch directly on your PR before it merges. It also checks dependency versions across services to catch conflicting package updates early.
Carrick ships with four skills for the most common agent failures — breaking a caller in another service, rebuilding existing code, trusting a stale copy of another service's type, and missing places in a codebase-wide change. Each skill gets its answer from the Carrick index. carrick init installs them into .claude/skills/ and .agents/skills/.
Skill | Use it | What it returns |
Before changing or deleting a route, handler, response shape, event or shared function, or to ask "who calls this?" | Everything that depends on the code you are about to change, with a file and line for each, and a type verdict for each consumer | |
At the end of a task that added or changed functions, or to ask "does this already exist?" | The new functions compared against the whole function index, and the places the project has built the same thing twice | |
Before changing a request or response type, or when a compatibility verdict names a problem you cannot place | The producer's type, each consumer call site's expected type and the stored verdict, side by side, one operation at a time | |
For "find every place that does X" questions | Every match for two wordings of one concept, paged to the end and joined into one list with a receipt |
"Which functions handle webhook signing across our services?"
"Where do we deduplicate users by email?"
"What calls /api/users, and what response shape does each caller expect?"
"Show me every function that retries on rate-limit errors."
The MCP endpoint exposes the index as structured tools your agent can call directly. The MCP tools reference lists each tool's parameters and response.
Tool | Purpose |
| Search functions by what they do, matching a plain-English query against each function's intent |
| Find similar functions, for code you are about to write or duplicates already in the project |
| Browse indexed functions and intents, a page at a time, by service or file |
| Show the project map, a short summary of services, contracts and unmatched calls |
| List workspace projects and the repositories connected to each |
| List the project's services, with their endpoint, call and function counts |
| Show the cross-service call graph, with unmatched calls and orphaned endpoints |
| Find who serves and calls an operation, given its method and path |
| Find callers of a function anywhere in the project |
| List a service's operations across HTTP, GraphQL, WebSockets and pub/sub |
| Read an endpoint's request and response types as the TypeScript compiler resolved them |
| Resolve a named type definition to its expanded TypeScript |
| Check a consumer against a producer, with a type verdict for each call |
| Read npm dependencies and version conflicts, for one service or across the project |
| List outbound calls to external targets, such as SDK calls, external domains and env-var URLs |
| Compare consumer and producer types, operation by operation |
| Generate Carrick setup files (the workflow, a Carrick skill, |
The GitHub Action refreshes each repository's part of the index on every push to main. It runs read-only in CI, with no API key to store.
name: Carrick
on:
push:
branches: [main]
pull_request:
branches: [main]
permissions:
id-token: write
contents: read
jobs:
carrick:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
- uses: carrick-tools/carrick@v1Building the index has the full workflow, with on-demand rescans, dependency installs and monorepo setup.
Carrick has a free tier, and paid plans are on the pricing page. The scanner in this repository is source-available under the Elastic License 2.0. Copyright (c) 2026 Far Harbour B.V.
See AGENTS.md for build, test, and contribution conventions.
cargo test
cargo fmt
cargo clippyInstall the optional pre-commit hook to run formatting and tests before each commit:
./scripts/install-hooks.shThis server cannot be deployed
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
Codebase intelligence for AI agents — dead code, blast radius, ownership.
Search indexed code, trace dependencies, assess change impact, and recall repository memory.
Versioned documentation registry and semantic search for AI tools and coding assistants.