BrowseFull catalogOutcomesSolve a specific problemRolesStack by teamTrustFilter by risk tier
← Back to the Claude Observatory

Sourcegraph

Connector Development Poor
Works inClaude Code Claude Cowork Claude Chat
Poor Scanned — metadata only

Eliminates time spent context-switching between repos and tools during code review, incident response, or refactoring.

Read-only enterprise code-search connector — semantic search, symbol lookup, and repo navigation across private/multi-repo codebases, with OAuth 2.0 or access-token auth and RBAC scope-pinning (mcp scope).

FreeNo code needed
Built and maintained by Anthropic, the makers of Claude.

Eliminates time spent context-switching between repos and tools during code review, incident response, or refactoring. Enables semantic understanding of large codebases without local cloning or manual grep workflows.

Engineering teams and architects navigating multi-repo systems or investigating cross-service dependencies at scale.

Claude Code Claude Cowork Claude Chat

https://claude.com/connectors/sourcegraph

By Sourcegraph

How to Get It

Option 1: Claude Desktop AppOpen the Customize panel in the sidebar → browse connectors → search and add. Works in Claude Code, Claude Cowork, and Claude Chat.
First thing to try

Once it’s connected, paste this into Claude:

Find all usages of a deprecated API function across my codebase

Trust Signals Auto-scanned

Not yet scanned. Learn how to check this tool yourself.

Data & Access

Data processingProcessed by Anthropic (the makers of Claude)

Community Pulse Growing

Discussed on Hacker News

3 mentions across 1 sources

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 0 GitHub stars; contributors unknown; commit recency unknown; license no license.

Things to check

  • Gated to Sourcegraph Enterprise plans — not usable for a client on a lower tier; GA/beta status not explicitly labeled either way. Sentiment search unavailable this session (WebSearch budget exhausted) — not scored from community signal.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation

Ease of Use
1/5
Versatility
1/5
Reliability
1/5
Security
3/5
Overall score1.30 / 5.00 PoorEvaluatedOct 2026
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 0 GitHub stars; contributors unknown; commit recency unknown; license no license.

← Back to the Claude Observatory

Rolling Claude out in your org? Let's talk.

Start a conversation →