Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
RepoPilot is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Repository evidence for agents before they adopt dependencies, enter codebases, compare, or merge.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http repopilot-mcp https://repopilot.app/api/mcp
# 2 — ask your agent for something these tools do
# check_dependency, evaluate_dependency_change, verify_dependency_change and 5 more
RepoPilot costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http repopilot-mcp https://repopilot.app/api/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
8 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
CALL when the user or agent is about to add, upgrade, trust, fork, or deploy an npm package or public GitHub repository. Returns a lean repository-level recommendation, confidence, evidence gaps, CVEs, maintenance, ownership, license, CI/tests, Scorecard, freshness, and next actions. DO NOT use for code navigation. Pass exactly one of repo or package. A favourable result does not validate an exact
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repo | string | no | Public GitHub repository as owner/repo or a github.com URL. |
| package | string | no | npm package name, for example lodash or npm:@scope/pkg. To judge a specific VERSION rather than the package as a whole, use evaluate_dependency_change instead. |
| owner | string | no | Repository owner, when repo carries only the bare name. Optional: prefer the single owner/repo form in repo. |
CALL immediately before adding or upgrading an npm dependency. Answers "is this exact version safe to take on" from registry metadata, advisory deltas (for the version itself and for every package in the dependency tree a fresh install resolves to), provenance, license, and repository evidence, and returns blockers, warnings, a recommendation, and a verification plan. Example: {"dependency":"lodas
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dependency | string | yes | A STRING: the npm package name on its own, with no version and no surrounding object — "lodash", "@types/node". Not {"name":...}, not {"lodash":"^4.17.0"}, not a list, and never wrapped in a top-level |
| to_version | string/number | no | The version you intend to install — an exact version ("4.18.1"), a dist-tag ("latest"), or a SemVer range ("^4.17.0"). A quoted string is preferred; a bare JSON number ("to_version": 19) is also accep |
| from_version | string/number/null | no | The version currently installed, or omitted when adding a new dependency. A bare JSON number is accepted the same way as to_version. Supplying it produces a before/after advisory comparison. |
| dependency_type | string | no | Where the dependency goes, in THESE words: "runtime" for a dependencies entry, "development" for devDependencies. The manifest and CLI spellings ("dev", "devDependencies", "--save-dev", "prod") are ma |
| package_manager | string | no | Optional. Only affects the commands and lockfile named in the verification plan. Inferred from project.lockfile_path when you send a project snapshot, and assumed to be npm otherwise. |
| project | object | no | Optional, source-free facts about the project you are changing. Supplying it adds Node/peer/license compatibility and a command-level verification plan. Omit it entirely and compatibility comes back " |
| policy_profile | string | no | Named team dependency policy. Strict requires provenance and denies package install hooks. Must be spelled exactly — a near-miss spelling is rejected rather than guessed, because reading it wrong woul |
| intent | string | no | Optional free text describing why you are making this change. Advisory only; it changes no verdict. |
CALL after changing the manifest/lockfile and running local checks. Compares the exact evaluated target with the resolved result and caller-reported proof receipts, checks every version in resolved_changes for advisories (list all packages the lockfile change added or changed), reports missing/failed evidence and residual risk, and labels receipts as caller asserted. It never runs commands or stor
| Parameter | Type | Required | Notes |
|---|---|---|---|
| evaluation | object | yes | The verification_context object exactly as evaluate_dependency_change returned it, passed back unchanged. Its signature covers every field, so edit nothing inside it. Sending the whole evaluate result |
| after | object | yes | — |
| diff | string | no | — |
| checks | array | yes | — |
CALL to investigate behavior in public source: supply question and relevant path_hints found from actual usages, for up to four files with commit-pinned line citations. checked_sha selects a commit; base_sha adds before/after excerpts; pr selects a public PR and observes its head's GitHub check runs. source_ranges retrieves missing context at pinned revisions, up to 40 lines per range. Selection i
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repo | string | no | Public GitHub repository as owner/repo or a github.com URL. |
| package | string | no | npm package name, for example lodash or npm:@scope/pkg. To judge a specific VERSION rather than the package as a whole, use evaluate_dependency_change instead. |
| owner | string | no | Repository owner, when repo carries only the bare name. Optional: prefer the single owner/repo form in repo. |
| question | string | no | — |
| checked_sha | string | no | Immutable head revision; required with source_ranges. |
| base_sha | string | no | Compare source at this base commit; omit when using pr. |
| pr | integer | no | Public PR number in repo. Requires question. Omit base_sha. |
| path_hints | array | no | Scope retrieval to these repository-relative files or directories. Requires question. |
| source_ranges | array | no | Read only these exact ranges, at most two per file/side and 40 lines per range. Requires question and checked_sha; base side also requires base_sha. Paths must fall within path_hints when supplied. Om |
CALL before editing an unfamiliar public repository, or to find where a bug or feature lives. Pass the issue or task text (up to 4000 characters; include the error and expected behaviour) and checked_sha when you know it. Returns files ranked for the task at that commit (provenance task_localizer), the owning layer, a bounded reading order, dependency consumers, test/verification obligations, anal
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repo | string | no | Public GitHub repository as owner/repo or a github.com URL. |
| package | string | no | npm package name, for example lodash or npm:@scope/pkg. To judge a specific VERSION rather than the package as a whole, use evaluate_dependency_change instead. |
| owner | string | no | Repository owner, when repo carries only the bare name. Optional: prefer the single owner/repo form in repo. |
| task | string | yes | — |
| checked_sha | string | no | — |
| intent | object | no | — |
| max_files | integer | no | — |
| path_hints | array | no | Optional repository-relative files or directories to prioritize. |
CALL before substantial code work in an unfamiliar repository when the agent needs key files, entry points, architecture hypotheses, a reading order, and verify-before-trusting guidance. Returns the cached CLAUDE.md-style artifact or Cursor rules. Do not call again if the artifact is already in context. Takes NO artifact id: name the repository itself. Minimal call: {"repo":"vercel/next.js"}. Pass
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repo | string | no | Public GitHub repository as owner/repo or a github.com URL. |
| package | string | no | npm package name, for example lodash or npm:@scope/pkg. To judge a specific VERSION rather than the package as a whole, use evaluate_dependency_change instead. |
| owner | string | no | Repository owner, when repo carries only the bare name. Optional: prefer the single owner/repo form in repo. |
| format | string | no | Optional. markdown for CLAUDE.md-style guidance (the default); cursor for .mdc rules. |
CALL when the user is choosing between exactly two dependencies or repositories. Returns the preferred candidate for each use case, material trade-offs, confidence, and evidence gaps. Each target is owner/repo, a GitHub URL, an npm package name, or npm:@scope/pkg. Cached full analyses are preferred; a miss uses bounded live GitHub/OpenSSF evidence with limited confidence and explicit unknowns rath
| Parameter | Type | Required | Notes |
|---|---|---|---|
| a | string | yes | First repo or npm package target. |
| b | string | yes | Second repo or npm package target. |
CALL before merging a pull request or after producing a local diff. Returns a deterministic 0-10 change-shape score with receipts for size, spread, missing tests, sensitive paths, hotspots, and blast radius. Pass repo+pr OR diff; repo may accompany diff for cached hotspot context. This prioritizes review and never approves a merge.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repo | string | no | owner/repo or a github.com URL. |
| pr | number/string | no | Positive pull request number, used with repo. |
| diff | string | no | Raw unified git diff to score directly. |
| files | array | no | Privacy-preserving changed-file facts; contains no source or diff hunks. |
| contract_id | string | no | Optional short-lived contract_id returned by plan_repo_task. |
| base_sha | string | no | — |
| head_sha | string | no | — |
| proofs | array | no | — |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install RepoPilot or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 2.0.1.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish RepoPilot can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.