carrickBLOCK
Carrick maps your entire TypeScript codebase across services and repositories, giving AI agents full context on existing types, routes, and function behaviours over MCP before they write duplicate or breaking code.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
TypeScript codebase intelligence for AI agents & IDEs.
[](https://mcpservers.org/servers/carrick-tools/carrick) [](https://github.com/marketplace/actions/carrick-typescript-context-engine) [](https://glama.ai/mcp/connectors/io.github.carrick-tools/carrick) [](https://claude.ai/directory/connectors/carrick) [](https://www.npmjs.com/package/carrick) [](https://open-vsx.org/extension/carrick-tools/carrick) [](https://registry.modelcontextprotocol.io/v0/servers?search=io.github.carrick-tools/carrick)
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. Th
2e34542cf4bfOBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add support-desk --env BILLING_KEY=${BILLING_KEY} --env FORGE_API_KEY=${FORGE_API_KEY} --env REALTIME_KEY=${REALTIME_KEY} --env SERVICE_SECRET_KEY=${SERVICE_SECRET_KEY} -- npx -y [email protected]{
"mcpServers": {
"support-desk": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"BILLING_KEY": "${BILLING_KEY}",
"FORGE_API_KEY": "${FORGE_API_KEY}",
"REALTIME_KEY": "${REALTIME_KEY}",
"SERVICE_SECRET_KEY": "${SERVICE_SECRET_KEY}"
}
}
}
}Exposed tools (2)
0 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
cancel-order | write | |
lookup-order | write |
Trust audit
BLOCKgrade F · trust 50/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (6 observation(s))
- Network
- declared (9 observation(s))
- Shell
- declared (9 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (25)
log(`recorded ${found.length} new function(s) for ${payload.session_id}`);if (spoken) log(`named ${spoken.named} new function(s) to the model, of ${spoken.found} recorded`);if (spoken) log(`named ${spoken.named} new function(s) to the model, of ${spoken.found} recorded`);let service_create = function("NoticesService.create", "/repo/src/notices.service.ts", 8);"packages/storage-kit/beacon.ts",
"Beacon.client.capture",
"beacon-metrics"
rows_for(&worker(), "packages/storage-kit/beacon.ts"),
"Beacon.client.capture".to_string(),
try { url = new URL(req.url ?? "/", "http://127.0.0.1"); }const redirect = `http://127.0.0.1:${address.port}/callback`;"CARRICK_PROMPT_ENDPOINT must be http://127.0.0.1:<port> or http://[::1]:<port>, not '{value}'."for ok in ["http://127.0.0.1:8080", "http://[::1]:8080"] {.release-please-manifest.json
.lsp.json
.vscodeignore
infer-carrier-transport-payload.test.ts
infer-payload-walk.test.ts
infer-response-helper-payload.test.ts
# Cross-repo accuracy eval (S4 thin slice, #203): scores the live scanner over
cd ../../tests/fixtures/imported-routers && npm install
import { manifest } from "../../platform/build.mjs";assert.equal(sessionFile("../../etc/passwd", dir), null);record("../../etc/passwd", [fn("slugify")], dir);assert.deepEqual(readSession("../../etc/passwd", dir).found, []);Gates applied: no_behavioural_pass.
2e34542cf4bffull audit observations/trust-audit/mcp-server/carrick-tools__carrick.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 2e34542cf4bf | BLOCK | F | 50 | first audit |
Questions
What is the carrick MCP server?
Carrick maps your entire TypeScript codebase across services and repositories, giving AI agents full context on existing types, routes, and function behaviours over MCP before they write duplicate or breaking code.
What tools does carrick expose?
2 in total: 0 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is carrick safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (50/100) and found 4 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does carrick need?
It reads BILLING_KEY, FORGE_API_KEY, REALTIME_KEY and SERVICE_SECRET_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does carrick run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as support-desk at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (2e34542cf4bf), read on 2026-10-11. The repository is watched and re-audited when it changes.