repoctx MCP server

Read from the package source without running it. The installed server may list more.

• agent_experience

  Score Agent Experience (AX): a single 0–100 number answering "how cheap and safe is it for an agent to make this change here?", blending Changeability (token cost), Containment (blast radius), Guardrails (tests / validation / CODEOWNERS / CI), and Clarity (task groundedness). Deterministic and composed from the change_impact, token-estimate, and CODEOWNERS engines — no new analysis. Returns sub-sc

• change_impact

  Given a plain-English change request, rank the files most likely to own the change, with risk flags, suggested tests, and an implementation plan. Optional diff base validates predictions against actual changed files. Writes a local .dev-context/index.json cache into the target repo; the call is idempotent and does not change source files.

• context_pack

  Generate a task-aware local context packet with primary files, related files, tests, patterns, and validation commands. Writes a local .dev-context/index.json cache into the target repo; the call is idempotent and does not change source files.

• convergence_score

  Score convergence: a deterministic 0–100 measure of the distance between a stated task (intent) and the actual git diff (execution), with sub-scores for Coverage (did the intent happen?), Scope (did only the intent happen?), and Risk alignment (did unrequested drift land on risk-sensitive paths?). Composed from the change_impact diff comparison and the shared risk vocabulary — no model, no new ana

• repo_harness

  Generate setup, validation, runtime, and context commands for an agent or CI harness.

• repo_index

  Index local repositories: generate .dev-context indexes and add them to the local catalog. Pass discover:true to find repository roots under the given paths first. Pass dryRun:true to discover and report without writing any indexes or catalog (read-only); this replaces the old repo_discover tool. Without dryRun this mutates the persistent local catalog, so it is not a pure read.

• repo_inspect

  Inspect repository shape, languages, package managers, script names, entrypoints, and git metadata. Returns up to 200 representative file paths; pass includeScripts:true to get full script command bodies instead of just names.

• repo_map

  Map a repository into a compact JSON code map, optionally narrowed by domain, file kind, or controller route. Pass domain to find files for a feature, kind to find files of a type (route, controller, service, apiClient, component, test), or route to match Nest controller routes by substring/regex. Replaces the old find_domain, find_file_kind, find_backend_route, and find_frontend_api_client tools.

• repo_search

  Search indexed local repositories by path, domain, kind, route, imports, exports, and symbols. Omit query to list the local repository catalog instead (the catalog listing the old repo_catalog tool returned). Only searches repositories already in the local catalog — if the catalog is empty this returns no matches, so call repo_index on the target repositories first.

• review_context

  Produce PR review context from local git diff metadata, optionally enriched with GitHub PR comments. Use review_context when you want the raw diff/comment context for a change, not a verdict. Use review_verdict instead for the full impact + review + gate composite, or review_gate for the gate verdict alone.

• review_gate

  Gate a change for merge and return a PASS / WARN / FAIL verdict. Omit pr to run the local, no-GitHub gate against a base ref (changed files, secret safety, risk-sensitive paths, release discipline, validation commands, dependency audit, policy profile). Set pr to gate an open GitHub PR via `gh` (PR state, review decision, CODEOWNERS approvals, unresolved conversations, branch protection, status ch

• review_verdictwrite action

  Run the full review pipeline in one shot: change_impact plus review_context plus review_gate, returning a unified verdict with a derived confidence score. Use review_verdict when you want the complete picture of a change in a single call. Use review_context instead for diff metadata only (no verdict), or review_gate for the gate verdict alone.

• workspace_report

  Generate a product-level report across multiple related repositories.

• Code scan50 source files scanned10/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 0 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10

Safety score

71/100

higher than 36% of 48,255 servers

Tools

13

the typical server has 7

Tools that change things

8%

typical: 0%. Fewer write tools means less an agent can break

GitHub stars

1

more than 65% of 28,688 servers

Downloads a week

59

more than 48% of 12,191 servers with a package

repoctx: common questions

Is repoctx MCP server safe?

Mostly: it is graded B (71/100). Read the repoctx safety report

How do I install repoctx?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does repoctx need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is repoctx maintained?

The last commit was 41 days ago (2026-09-24). The latest release is v2.6.0.

What can I use instead of repoctx?

Servers from other publishers that do the same job: Sem MCP server.

How does repoctx compare with other MCP servers?

safety score 71/100 (higher than 36% of 48,255 servers); tools 13 (the typical server has 7); tools that change things 8% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.