# SHPBL: Repository Audit & Repair (remote · shpbl.com) Audit and repair any public GitHub repo. Free survey; paid source, unified diffs and a pull request. - Trust score: 73/100 (medium) - Change this week: +4 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-09-20 ## Components - remote · `shpbl.com`: 73/100 (this document), [markdown](https://verifymcp.io/servers/com-shpbl-repository-audit-and-repair/api-public-mcp.md), [page](https://verifymcp.io/servers/com-shpbl-repository-audit-and-repair/api-public-mcp) - remote · `shpbl.com`: 38/100, [markdown](https://verifymcp.io/servers/com-shpbl-repository-audit-and-repair/shpbl.md), [page](https://verifymcp.io/servers/com-shpbl-repository-audit-and-repair/shpbl) ## Channel facts - Endpoint: `https://shpbl.com/api/public/mcp` - Transports: `streamable-http` - Auth: `none` - Version: `1.16.0` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-09-20. - **Endpoint Security**: 63/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - Authorisation not fully verified: no authorisation is required to call this server, and 16 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. - HTTPS is enforced; there's no plaintext access path. - The HSTS (Strict-Transport-Security) header is present. - DNSSEC check failed: this domain isn't protected by DNSSEC. - **Transport & Reachability**: 100/100 - Verified streamable-http transport via a live MCP handshake. - **Schema Quality & AI Usability**: 58/100 - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 10269 tokens (~604/item across 17 items; 17 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 64/100 - Stability check failed: schema churn in the 26 days we've observed: 1 tool removals, 4 breaking changes, 0 auth/transport breaks, 5 additions. - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - We read all 17 captured tool definition(s), and no name or description among them implies an irreversible operation. - An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. ## Install ### How do I install the SHPBL: Repository Audit & Repair MCP server? SHPBL: Repository Audit & Repair is a hosted endpoint at https://shpbl.com/api/public/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation. ### Claude ```bash claude mcp add --transport http com-shpbl-repository-audit-and-repair 'https://shpbl.com/api/public/mcp' ``` ### Cursor ```json { "mcpServers": { "com-shpbl-repository-audit-and-repair": { "url": "https://shpbl.com/api/public/mcp" } } } ``` ### VS Code ```json { "servers": { "com-shpbl-repository-audit-and-repair": { "type": "http", "url": "https://shpbl.com/api/public/mcp" } } } ``` ### Codex ```toml [mcp_servers.com-shpbl-repository-audit-and-repair] url = "https://shpbl.com/api/public/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "com-shpbl-repository-audit-and-repair": { "type": "remote", "url": "https://shpbl.com/api/public/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add com-shpbl-repository-audit-and-repair --url 'https://shpbl.com/api/public/mcp' --transport streamable-http ``` ### Hermes ```yaml mcp_servers: com-shpbl-repository-audit-and-repair: url: "https://shpbl.com/api/public/mcp" ``` ### Netclaw ```json { "McpServers": { "com-shpbl-repository-audit-and-repair": { "Transport": "http", "Url": "https://shpbl.com/api/public/mcp" } } } ``` ### Vellum ```bash assistant mcp add com-shpbl-repository-audit-and-repair -t streamable-http -u 'https://shpbl.com/api/public/mcp' ``` ### Other ```json { "mcpServers": { "com-shpbl-repository-audit-and-repair": { "type": "http", "url": "https://shpbl.com/api/public/mcp" } } } ``` The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs. ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-09-20 (score 73, +1) No change was recorded against any check on this day. Stability & Change Management went from 60 to 64. ### 2026-09-18 (score 72, +1) No change was recorded against any check on this day. Stability & Change Management went from 54 to 57. ### 2026-09-16 (score 71, +1) No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. ### 2026-09-14 (score 70, +1) No change was recorded against any check on this day. Stability & Change Management went from 40 to 44. ### 2026-09-12 (score 69, +44) - [security regression] Stability: unverified → fail - [security improvement] Injection markers: unverified → pass - [security improvement] Transport: fail → pass - [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 16 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. - [security] Tool “compose_capability” rewrote its description, which is the text the model reads - [functional improvement] Endpoint reachability: not serving MCP → reachable - [functional improvement] Tool coverage: unverified → 100 - [functional improvement] MCP protocol: unverified → pass - [functional] Server version: 1.47.0 → 1.47.1 - [cosmetic] “compose_capability” reworded the description of “grants” - [cosmetic] “compose_capability” reworded the description of “per_affordance” - [cosmetic] “harvest_repo” reworded the description of “per_affordance” - [cosmetic] “harvest_repo” reworded the description of “suppress_duplicates” ### 2026-09-10 (score 25, −42) - [security regression] Endpoint reachability: reachable → not serving MCP - [security regression] Tool safety: pass → unverified - [security regression] Stability: fail → unverified - [security regression] Transport: pass → fail - [security] Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the tool list to see what that exposes. - [functional regression] Tool coverage: 100 → unverified - [functional regression] Capabilities: pass → unverified - [functional] First check of Schema quality: unverified ### 2026-09-09 (score 67, 0) - [security] Tool “build_intent” rewrote its description, which is the text the model reads - [functional] Server version: 1.45.0 → 1.47.0 - [cosmetic] “harvest_repo” added an optional parameter “carry_notice_files” - [cosmetic] “harvest_repo” added an optional parameter “novelty_threshold” - [cosmetic] “harvest_repo” added an optional parameter “quality_floor” - [cosmetic] “harvest_repo” added an optional parameter “reuse_obligations” - [cosmetic] “harvest_repo” added an optional parameter “reuse_permitted” - [cosmetic] “harvest_repo” added an optional parameter “suppress_duplicates” - [cosmetic] “harvest_repo” added an optional parameter “upstream_project” - [cosmetic] “harvest_repo” reworded the description of “grants” ### 2026-09-08 (score 67, 0) - [security] Tool “library_search” rewrote its description, which is the text the model reads - [security] Tool “selfcheck_mcp” rewrote its description, which is the text the model reads - [security] Tool “harvest_repo” rewrote its description, which is the text the model reads - [functional] Server version: 1.41.0 → 1.45.0 - [cosmetic] “harvest_repo” added an optional parameter “approve” - [cosmetic] “harvest_repo” added an optional parameter “approved_by” - [cosmetic] “harvest_repo” added an optional parameter “cml_license” - [cosmetic] “harvest_repo” added an optional parameter “decline” - [cosmetic] “harvest_repo” added an optional parameter “governor_key” - [cosmetic] “harvest_repo” added an optional parameter “grants” - [cosmetic] “harvest_repo” added an optional parameter “host_license” - [cosmetic] “harvest_repo” added an optional parameter “mode” - [cosmetic] “harvest_repo” added an optional parameter “pages” - [cosmetic] “harvest_repo” added an optional parameter “per_affordance” - [cosmetic] “library_search” reworded the description of “scope” - [cosmetic] “harvest_repo” reworded the description of “brief” - [cosmetic] “harvest_repo” reworded the description of “part” - [cosmetic] Tool “harvest_repo” changed its title: Harvest a repository → Harvest capability out of a repository ## MCP tools (17) ### `welcome` (~113 tokens) Start here — welcome, tool menu and example commands Call this first, once, when a person connects. Returns the welcome, the full tool menu with one line per tool, the exact sentences a person can say to start a run, the support address, and the link to the user's manual. Free, unmetered, no key. Read it to the person in your own words — warmly and briefly — then ask what they would like to point it at. Input parameters: - `name` (string): The person's first name, if you know it, so the greeting can use it. ### `list_repos` (~309 tokens) List the repositories I can work on (free) Lists real repository names so a run never starts on a guessed one, and answers whether a repository can be written to. Pass `github_token` to see everything that token can see, or `owner` to list a public account's repositories; with neither, it lists the repositories the SHPBL GitHub App is installed on for this key — the same ones a pull request can be opened on. Pass `repo: "owner/name"` to ask about one target instead of reading the whole list. Free — costs no allowance. Input parameters: - `github_token` (string): A GitHub token (PAT or fine-grained) to list with. Never stored, never logged — used for this call only. - `key` (string): Your SHPBL key (shpbl_mcp_…), only needed to list App-connected repositories. Optional if sent as the Authorization header. - `limit` (integer): How many repositories to return (default 30, max 100). - `owner` (string): A GitHub user or organisation to list the public repositories of, when no token is available. - `page` (integer): Which page of the connected-repository list to return, 1-based. Use this rather than a higher `limit` past 100; the response names the next page when there is one. - `repo` (string): Ask about one target, `owner/repo`: whether this key may open a pull request on it. Call this before offering to write. ### `method_protocol` (~100 tokens) The SHPBL method, in full Return the SHPBL disciplines verbatim — evaluation, remediation and harvest — plus the component classes' verification axes and the reporting style. Free and unmetered. Fetch it once, then call `fix_repo` or `harvest_repo` with `brief: true` so their payload is source rather than repeated instructions. Input parameters: - `stage` (string): One stage only: `evaluate`, `fix` or `harvest`. Omit for all three. ### `run_contract` (~349 tokens) The canonical run contract, and the gate that executes it Read the canonical twelve-step run contract, or check a run bundle against it. Call it with no `files` to get the contract itself: every step's id, the artifacts it must produce, the exact condition that closes it, the terminal word to report when it does not, the instruction-precedence order, the retention rule and the two legal ends of step 12. Call it with `files` — a map of run-folder paths to their text — to get the machine verdict: which step blocked, which predicate refused and why. This is the identical implementation the offline `tools/run-gate.mjs` in every edition is bundled from, so the two cannot disagree about whether a bundle satisfies the contract. What they do not share is evidence: the offline gate checks the bundle you hand it, while a connected run can also confirm against the real repository tree that the files cited exist and say what the bundle claims. Same rules, one with a witness. Free, unmetered, read-only, stateless. Never infer a step, reorder one, or declare a run finished on your own reading — run the gate and report its word. Input parameters: - `files` (object): The run bundle as `path: text`, relative to the run folder (for example `STEP-LEDGER.json`). Send the canonical outputs you have; the gate says what is missing. Bounded: at most 400 entries and 8 MB… - `through_step` (integer): Evaluate gates through this step only. Defaults to 12. ### `pin_source` (~275 tokens) Pin a repository for step 1 Build `HOST-SOURCE-MANIFEST.json` for canonical step 1 from a GitHub repository, online, with no clone and no download: every file's Git blob identity, the byte length, the head commit, and the `SHPBL-SOURCE-DIGEST/1` digest over the pinned tree. Write the returned JSON to your run folder as `HOST-SOURCE-MANIFEST.json` and step 1 passes the gate. Free and unmetered. If the run is offline instead, do not call this — run `node tools/source-manifest.mjs ` from the edition, which produces the same manifest from a directory or straight out of the repository ZIP. Never invent the digest or the commit. Input parameters: - `github_token` (string): Optional GitHub token (Contents: read) for a private repository. - `key` (string): Your SHPBL key, if you have one. Optional — this tool is free; a key only helps reach a private repository through a connected GitHub App install. - `label` (string): What to call the target in the manifest. Defaults to `owner/repo@branch`. - `repo` (string, required): A GitHub repository: `owner/repo`, a github.com URL, or `owner/repo#branch`. ### `evaluate_repo` (~638 tokens) Audit a repository Audit any GitHub repository and get back one complete result: a report (inventory, languages, spine files, risk signals), the capabilities found in it (name, signature, file and line, stated contract, dependencies), and how it stands against SHPBL's anonymous corpus of audited repositories. Works with no key: every caller gets the whole diagnosis of their own repository. A free run stops at the composition boundary — neither library is searched, so no library rows, candidates, parents or proposed architecture are returned — and nothing is retained (no pull request, no export, no recorded run). A Practitioner key (7-day free trial) continues past that boundary: both libraries searched, candidates identified and composed, and the result written back to your own repository. Whatever a run finds is yours. Follow with `fix_repo` for verbatim source and diffs, `harvest_repo` for the whole tree. Input parameters: - `as_free` (boolean): Run at the free depth even when the key carries a paid tier, so you can see exactly what a caller without a subscription is handed. Costs no allowance and changes nothing else about the audit. - `brief` (boolean): Default true: keep the audit compact and do not include the full method protocol. Set false to include the protocol block. - `github_token` (string): Optional GitHub token (Contents: read) for a private repository. Not needed if the owner connected the SHPBL GitHub App to this key at https://shpbl.com/mcp-access. - `key` (string): Your SHPBL key (shpbl_mcp_…), if you have one. Optional — without it the audit runs at the free depth. Also read from the `Authorization: Bearer …` header. - `own_library` (array): Your own previously harvested capabilities, read out of your repository's `.shpbl/` library and passed back in. Optional. When present, this run checks your concerns against your own library first an… - `protocol_ack` (boolean): Set true to say you already hold the SHPBL protocol. The discipline, the ten meta capabilities, the hands-off list and the return shape are then not reprinted even when `brief: false` — they are unch… - `repo` (string, required): A GitHub repository: `owner/repo`, a github.com URL, or `owner/repo#branch`. - `sections` (array): Which sections to print, when you only need some of them. Omit it and the whole audit comes back, which is the right default on a first call. On a follow-up — re-reading the capability list after a r… ### `fix_repo` (~487 tokens) Repair a repository The repair: verbatim source of the files you name — or the repository's spine when you name none — paginated for your context window, with the remediation protocol your model writes the diffs against. Free to run with no key: every file you name, paginated, plus the ordered remediation protocol — repair of what is already there. A free repair stops before either library is searched, so it proposes no composed capability, no candidates and no reuse. A Practitioner key (7-day free trial) crosses that boundary and makes the repair persist — `write_to_repo` opens the branch and the pull request. Input parameters: - `brief` (boolean): Skip the remediation protocol preamble and return source with a one-line reminder instead. Use it once you already hold the method — `method_protocol` (free) returns it whenever you need it again. - `github_token` (string): Optional GitHub token (Contents: read) for a private repository. Not needed if the SHPBL GitHub App is connected to this key. - `key` (string): Your SHPBL key (shpbl_mcp_…), if you have one. Optional — without it the repair returns one file at the free depth. Also read from the `Authorization: Bearer …` header. - `own_library` (array): Your own previously harvested capabilities, read out of your repository's `.shpbl/` library and passed back in. Optional. When present, this run checks your concerns against your own library first an… - `part` (integer): Which page of source to return. Page 1 reports the total and carries the protocol. - `paths` (array): Paths to read, from the evaluation. Omit to read the repository's spine. - `protocol_ack` (boolean): Set true to say you already hold the SHPBL protocol — the discipline, the ten meta capabilities, the hands-off list and the return shape are then not reprinted on page 1. Same effect as `brief` for t… - `repo` (string, required): A GitHub repository: `owner/repo` or a URL. ### `harvest_repo` (~1345 tokens) Harvest capability out of a repository The harvest shortcut: point it at a repository you hold a licence to reuse — one you do not own and will never open a pull request against — and it goes straight to the capabilities. It reads what that repository can already do, fuses those affordances with the owned SHPBL capability library, ranks and names the results as proposals a person can read, stops for your decision on each one, and then emits the seed modules for exactly the ones you approved into your own `.shpbl/` library. That is the gauntlet's steps 8, 9 and 10 without the audit, the repair plan or the pull request. It never writes to the target repository. Pass `approve` with `approved_by` and `host_license` to collect the approved grants; pass `mode: "walk"` for the older batched ledger walk of the whole tree (`estimate`, `part`, `ledger_digest`, `budget` belong to that mode). Free calls report what the repository can do and what is offerable against it, then stop at the composition boundary; grants need a Practitioner key (7-day free trial). Input parameters: - `approve` (array): Harvest mode: the grant ids the person approved. Only these are emitted. Omit it on the first call — the proposals have to be put to them first. An id nobody proposed refuses the whole set rather tha… - `approved_by` (string): The name of the person who approved them. Required with `approve`. An agent, a model, a vendor, a policy or a default is refused, not recorded. - `brief` (boolean): Walk mode only: skip the harvest protocol preamble on batch 1 and spend the payload on source. Use it once you already hold the method — `method_protocol` (free) returns it verbatim. - `budget` (number): Characters per batch — a whole number from 10,000 to 120,000. Defaults to 90000; lower it for a smaller context window, raise it only if the client can carry it. Out-of-range values are refused in pl… - `carry_notice_files` (array): Licence or notice files from the host that must be copied into the artifact. Detected candidates are reported to you if you omit this. - `cml_license` (string): Your perpetual copy's licence key, if you hold one. It changes retention, never depth. - `decline` (array): Harvest mode: the grant ids the person explicitly said no to. Only these are recorded as declined; anything they were not asked about stays open and is re-offered, never written down as a refusal. - `estimate` (boolean): Return the size of the walk only — batch count, total characters, largest batch, split files — with no source. - `github_token` (string): Optional GitHub token (Contents: read) for a private repository. Not needed if the SHPBL GitHub App is connected to this key. - `governor_key` (string): Operator passphrase for SHPBL's own copy. Resolved by the server; it changes only where the harvest is staged, never what is proposed. - `grants` (number): Harvest mode: how many capability proposals to rank, 1 to 200. There is no fixed shallow ceiling any more — a sophisticated repository can support far more than a couple of dozen higher-order composi… - `host_license` (string): What the target repository's licence permits for this reuse, and any obligation it attaches — for example `MIT, attribution required`. Required with `approve`; SHPBL records your declaration and does… - `include` (string): Optional path filter — only paths containing this text are harvested. - `key` (string): Your SHPBL Practitioner subscription key (shpbl_mcp_…). Optional if your client sends it as the `Authorization: Bearer …` request header. - `ledger_digest` (string): The ledger folded so far, handed back by a previous session so this batch continues the same run instead of starting over. - `mode` (string): `harvest` (the default when nothing else in the call implies a walk) is the shortcut: proposals, your decision, then the seed modules for what you approved. `walk` is the older batched ledger walk of… - `novelty_threshold` (number): Harvest mode: how different a proposal must be from the higher-ranked ones already chosen, 0 to 1, measured on bound capabilities and title vocabulary. 0 suppresses only exact duplicates; 0.4 is firm… - `pages` (number): Harvest mode: how many source pages to read for evidence, 1 to 12 (about 90,000 characters each). Proposals are cut only from what was actually read. - `part` (number): Walk mode only: which batch to return, 1 to 2000. Batch 1 carries the protocol and the manifest; walk them all in order. - `per_affordance` (number): Harvest mode: how many proposals one host affordance may produce, 1 to 200. - `quality_floor` (number): Harvest mode: drop proposals scoring below this, 0 to 1. The score is a discovery aid for ordering what to read first — it is never evidence that a capability deserves to exist. - `repo` (string, required): A GitHub repository: `owner/repo` or a URL. - `reuse_obligations` (array): The obligations the licence attaches that must be preserved in the artifact — attribution, notice retention, share-alike, and so on. Recorded against every emitted artifact and carried into its manif… - `reuse_permitted` (boolean): Required with `approve`: the person's explicit statement that reuse of this upstream project is permitted for this composition. Absence is never a yes, and SHPBL does not infer permission from a dete… - `suppress_duplicates` (boolean): Harvest mode: drop proposals whose proposed composition is identical to a higher-ranked one. Default true. - `upstream_project` (string): The upstream project the reuse is declared against. Defaults to the repository being harvested. ### `compose_capability` (~346 tokens) Compose a new capability into a repository The harvest lane: read what a repository can already do, then offer codeless capability nominations that fuse those affordances with owned SHPBL primitive capabilities — DREAM, EVOLUTION, MEMORY, DEFENSE, BRAIN and the rest of the canonical forty, plus the S-Tier artifacts. Each nomination names host evidence, proposed capability bodies, Capability Contract slots, a test plan, and honest limits. It contains no implementation; approved materialization belongs to `harvest_repo`. Free calls return host affordances, then stop before library correlation; nominations require a Practitioner key (7-day free trial). Input parameters: - `github_token` (string): Optional GitHub token (Contents: read) for a private repository. - `grants` (number): How many codeless capability nominations to return, 1 to 200. Ranked by measured fit and capability standing. - `include` (string): Optional path filter — only paths containing this text are read for affordances. - `key` (string): Your SHPBL Practitioner subscription key (shpbl_mcp_…). Optional if your client sends it as the `Authorization: Bearer …` request header. - `pages` (number): How many source pages to read for affordance evidence, 1 to 12 (about 90,000 characters each). More pages means more of the tree is read; the grants are cut from whatever was read. - `per_affordance` (number): How many nominations one affordance may produce, 1 to 200. Raise it to see alternative leads for the same host capability. - `repo` (string, required): A GitHub repository: `owner/repo` or a URL. ### `build_intent` (~820 tokens) Register a Build Intent and resolve its licence The gate between discovery and creation, and the human checkpoint in front of it. Register one Build Intent — what you found in the host, what SHPBL already possesses, what new software becomes possible, why neither parent does it alone, and the tests that would prove it — and this returns the mechanical verdict: the invariants it passed, whether it rests on SHPBL's licensed reusable capability, whether this caller may execute the foundry, the terminal state to report, and where an authorised artifact may come to rest. THE CHECKPOINT BLOCKS: without `human_decision` carrying an attributed decision from the person, this returns the proposal in the words to say to them and nothing else — no verdict, no read, no record — and you end your turn and wait. No answer yet is NOT_YET_ASKED, never DECLINED. A decision attributed to you, to a model, to a policy or to a default is refused where the server can recognise it as such; any other name is recorded and attributed, not verified, and the authorization says which — `account` when the name matches the key's account holder, `attested` otherwise. DECLINED and NEEDS_EXPLANATION are successful outcomes: record them, build the approved siblings, and do not report a declined proposal as a failed step. Free to call at every level. Every COMPOSE, SPECIALIZE and CREATE must pass through this before any source is written; never assume authority and never write a refused artifact yourself. Input parameters: - `cml_license` (string): The licence key from a purchased Complete Master Library. Perpetual rights to that release count as execution authority on their own — no subscription needed. - `github_token` (string): Optional GitHub token (Contents: read) so the gate can read the host tree and prove the cited paths exist. Not needed if you pass `host_source_manifest`. - `governor_key` (string): Governor authority. Only a Governor-resolved call may stage an artifact for SHPBL's global corpus. - `host_source_manifest`: The `HOST-SOURCE-MANIFEST.json` from `pin_source` or `tools/source-manifest.mjs`, as JSON text or an object. Offline runs must send this: the gate recomputes its digest and resolves every cited path… - `human_decision` (object): The person's decision on this proposal. Step 9 is a blocking checkpoint: without an attributed human decision this tool returns the words to say and nothing else, and you end your turn there. Do not… - `intent` (object, required): The Build Intent record; every field it asks for is part of the evidence, and each field carries its own description in this schema. Required: `build_intent_id`, `proposed_artifact_id`, `proposed_nam… - `key` (string): Your SHPBL Practitioner key (shpbl_mcp_…). Optional if your client sends it as the `Authorization: Bearer …` header. ### `run_gauntlet` (~1128 tokens) Run the full gauntlet — Practitioner One runner for an entire SHPBL repository audit and repair: survey, opening library comparison, evaluation, repair, the batched harvest, closing library comparison, the branded HTML report, and the write-back path. STRICT SEQUENCE: call it once with no `step` for the run card, then `step: 1`, `step: 2`, one step per turn, in order. Do the returned step, report one line to the person, then call the next. Never call two steps in one turn, never attempt the whole run at once, and never infer a finding you were not handed. From `step: 2` on you must pass `ledger_digest`; every 3 steps (adjustable with `checkpoint_interval`, max 10, only when the person asks for fewer pauses) the run pauses and you must ask the person before continuing, then pass `continue_ack: "continue"`. The final step hands over the report template and the write-back path. Your own model does all reading and writing. This full conductor requires a Practitioner key (7-day free trial). The free lane provides repository evaluation, not a partial or full gauntlet. Input parameters: - `budget` (number): Characters per harvest step — a whole number from 10,000 to 120,000. Defaults to a moderate 45,000 so each step stays readable and cheap; raise it toward 90,000 only if the person asks for fewer, hea… - `checkpoint_interval` (number): How many harvest steps between check-ins with the person. Defaults to 3; raise it (up to 10) only when the person has asked for fewer pauses. Never set it silently — the check-ins are how the person… - `continue_ack` (string): The person's approval to continue past a checkpoint. Every 3 harvest steps this run pauses: report to the person, ask whether to continue, and only when they say yes call the next step with `continue… - `fold_token` (string): The `fold_token` returned by the previous step, passed back verbatim. Required from `step: 2` onward: it is signed by this server and carries the previous step's number and the hash of the ledger you… - `github_token` (string): Optional GitHub token (Contents: read) for a private repository. Not needed if the SHPBL GitHub App is connected to this key. - `include` (string): Optional path filter — only paths containing this text are in scope for the whole run. - `key` (string): Your SHPBL Practitioner subscription key (shpbl_mcp_…). Optional if your client sends it as the `Authorization: Bearer …` request header. - `ledger_digest` (string): The ledger folded so far, one line per capability, **each line carrying the file path it came from** (for example `src/lib/queue.ts — retry with backoff`). Required from `step: 2` onward — it is the… - `own_library` (array): Your own previously harvested capabilities, read out of your repository's `.shpbl/` library and passed back in. Optional. When present, this run checks your concerns against your own library first an… - `personality` (string): How the person wants to be spoken to for this run: technical, professional, friendly, light, coach, deadpan. Ask them once before step 0 and pass what they choose; it rides the run and changes wordin… - `protocol_ack` (boolean): Set true to say this session already holds the SHPBL protocol. The discipline, the ten meta capabilities, the hands-off list and the return shapes are then not printed on step 0 or step 1 — they are… - `repo` (string, required): A GitHub repository: `owner/repo`, a URL, or `owner/repo#branch`. - `step` (number): 0 to 2000. 0 (default) returns the run card and the plan with no source. 1…N walk the harvest batches, one per turn and in order. N+1 closes the run with the report template and the write-back path.… ### `library_index` (~245 tokens) What SHPBL publishes Everything published on shpbl.com in one read: the editions and their prices and licences, the seven volumes of The Strategic Master Library with their seals and read links, the public downloads with byte sizes, and the case studies of real audit runs with each verdict, and `pools` — the canonical reconciliation of every count this server quotes, so two totals are never mistaken for a contradiction and never added together. Scope it with `sections`, or pass `volume` (slug or 1-7) or `case_study` (slug) for one record in full. Free — no key, no allowance. Input parameters: - `case_study` (string): One case study in full, by slug — what the run got right and what it learned. - `sections` (array): Which sections to return. Omit for all of them: facts, volumes, editions, downloads, case_studies, pools. `pools` is the canonical reconciliation of every count this server quotes — read it before co… - `volume` (string): One volume in full, by slug or by number 1-7. Its complete text is a `library_document` call. ### `library_document` (~211 tokens) Read a library document Read one long SHPBL document, paged for a context window: `volume` (the complete text of a volume of The Strategic Master Library), `catalog_outline` (the Collective catalog's parts, component classes, agent-kit steps and verification axes), `report_template` (the branded audit report HTML to fill in), or `standing_order` (the prompt that governs a run). Requires a Practitioner key. Input parameters: - `document` (string, required): Which document to read. - `key` (string): Your SHPBL subscription key (shpbl_mcp_…). Optional if your client sends it as the `Authorization: Bearer …` request header. - `part` (number): 1-based page of the document, up to 60. - `section` (string): For `document: catalog_outline` — only parts or sections whose name contains this text. - `volume` (string): Required for `document: volume` — the volume slug or its number, 1 through 7. ### `library_search` (~544 tokens) Search the capability library Search the Collective Master Library for a capability in plain words, before writing new code. `scope: "catalog"` (Practitioner) searches the engineered components — class, what each does, API surface, line counts, verification marks. `scope: "composites"` searches capabilities earlier runs invented for one host by fusing library parts, each citing its sealed report. Pass `ids` for whole rows by component ID, with siblings and declared twins. Multi-word queries match term by term and rank; with no exact hit you get the closest rows, labelled as such. Input parameters: - `certified_only` (boolean): Crown jewels only: return only rows whose body the certification harness executed and read clean (CERTIFIED or PROVISIONAL). This withholds the INCONCLUSIVE rows — bodies the harness could not exerci… - `component_class` (string): Catalog only: restrict to one component class, e.g. `CrownJewel/S-Tier`, `Block/Engine`. Substring match. - `ids` (array): Up to 20 component IDs (e.g. `STIER-S-84`, `BLD-ENG-303`) returned in full instead of a search. - `include_siblings` (boolean): With `ids`: also list up to 12 other component IDs in the same class, for comparison. - `key` (string): Your SHPBL subscription key (shpbl_mcp_…). Optional if your client sends it as the `Authorization: Bearer …` request header. - `limit` (number): Alias for `page_size`, 1 to 50. Given both, `page_size` wins. - `pack` (string): Vault only: restrict to one vertical pack, e.g. `fintech-v1`. Substring match. - `page` (number): 1-based page of results. A page past the end is refused, never returned empty. - `page_size` (number): Rows per page, 1 to 50. Defaults to 20. - `query` (string): Plain-words capability, name, ID or API symbol. Omit to page the whole pool. - `scope` (string): `catalog` — engineered components (Practitioner). `crown-jewels` — the S-Tier Vault of standalone lab-curated artifacts. `composites` — capabilities past runs invented for one host. (`vault` is no lo… ### `selfcheck_mcp` (~134 tokens) Audit this server against its own axes (free) Runs SHPBL's own audit against the running server and returns one pass/fail/unavailable line per verification axis: the registered tool surface against the priced tier table, version agreement across the published files, subscription-register reachability, catalog reachability, repository-write authority, and billing wiring. Free, unmetered, read-only — nothing is written and no model is called. Use it to prove the server is live and consistent before starting a run, or when a tool answered in a way that looks wrong. Input parameters: - `verbose` (boolean): Include the full tool-to-tier table and the axis definitions in the answer. ### `subscription_status` (~91 tokens) Subscription status Report the tiers of this MCP server and — from the `key` argument or the same `Authorization` header the gated tools read — that key's tier, status and month-to-date usage. This is the authoritative answer to "am I connected, and what do I have". Input parameters: - `key` (string): Optional SHPBL subscription key. Omit it if your client sends the key as a request header. ### `write_to_repo` (~1099 tokens) Open a pull request (Practitioner) Land finished work in a repository as a pull request: pass the files you wrote (full new contents, not diffs) and this opens a branch and a PR for the human to review and merge. Nothing is ever pushed to the default branch. Requires a SHPBL Practitioner key and the SHPBL GitHub App installed on that repository (or a one-off `github_token`). The caller chooses the repository — ask which one, or call `list_repos` first; never assume. Where things go: Harvest output belongs under `.shpbl/` in **the caller's own repository** — the person who asked for the run — and never in the repository that was harvested. Those are frequently not the same repository: a run may read a public open-source project, or a repository the caller merely has access to, and writing a harvest back into a source repository would be putting our output into somebody else's software. Sources a run may read: public repositories that carry a proper open-source license, the caller's own repositories, or private repositories the caller has access to. The server never reads a repository the caller has no right to read, and it never absorbs customer harvests back into the public library. \- `.shpbl/README.md` — the index of their capability library (this tool scaffolds it when it is absent). \- `.shpbl//LEDGER.md` — the folded ledger for one run. \- `.shpbl//REPORT.html` — the branded report, if one was produced. \- `.shpbl//` — a capability kept as source, one folder each. \- `.shpbl/COMPOSITES.md` — your own composites: capabilities this run invented for your repository by fusing parts that did nothing alone. Record each as `- — — `. These are yours and stay private; SHPBL's global composites ledger is fed only by Governor-keyed published runs, so never send yours anywhere and never expect them to appear there. If the harvested repository is not the caller's own, the harvest still lands in the caller's `.shpbl/` and the s… Input parameters: - `base_ref` (string): Branch to open against. Defaults to the repository's default branch. - `branch` (string): Branch to write on. Defaults to one derived from `run_id`, or `shpbl/-`; reusing a name appends to that PR. - `build_authorization` (array): The signed build authorizations `build_intent` returned, one per artifact this pull request lands. Required when `kind` is `foundry`: the server verifies each against its own Build Intent ledger and… - `files` (array, required): Complete file contents to commit. For a repair, the whole fixed file — not a diff. - `github_token` (string): One-off GitHub token with Contents and Pull requests write. Used for this call only and never stored. Omit it if the SHPBL GitHub App is installed. - `key` (string): Your SHPBL subscription key (shpbl_mcp_…). Optional if your client sends it as the `Authorization: Bearer …` request header. - `kind` (string): What this pull request lands. `harvest` means kept capabilities and a ledger: write them under `.shpbl/` and this scaffolds `.shpbl/README.md` as the index of their own capability library when it is… - `repo` (string, required): The GitHub repository to write to: `owner/repo` or a URL. - `run_id` (string): A stable id for this piece of work (a harvest run seal, a repair order id). Retrying with the same run_id lands on the same branch and updates the same pull request instead of opening a second one. P… - `summary` (string, required): Pull request body: the repair order, or the run seal and coverage of a harvest. Markdown. - `title` (string, required): Pull request title — say what the change does. ## Diagnostics Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-shpbl-repository-audit-and-repair/api-public-mcp#diagnostics ## Score history - 2026-09-20: 73 - 2026-09-19: 72 - 2026-09-18: 72 - 2026-09-17: 71 - 2026-09-16: 71 - 2026-09-15: 70 - 2026-09-14: 70 - 2026-09-13: 69 - 2026-09-12: 69 - 2026-09-11: 25 - 2026-09-10: 25 - 2026-09-09: 67 - 2026-09-08: 67 - 2026-09-07: 67 - 2026-09-06: 66 - 2026-09-05: 66 - 2026-09-04: 65 - 2026-09-03: 65 - 2026-09-02: 65 - 2026-09-01: 64 - 2026-08-31: 64 - 2026-08-30: 65 - 2026-08-29: 65 - 2026-08-28: 64 - 2026-08-27: 53 - 2026-08-26: 64 - 2026-08-25: 63 ## Common questions ### What is the SHPBL: Repository Audit & Repair MCP server? SHPBL: Repository Audit & Repair is an MCP server listed in the public MCP registry as com.shpbl/repository-audit-and-repair. Audit and repair any public GitHub repo. Free survey; paid source, unified diffs and a pull request. This page covers its hosted endpoint (https://shpbl.com/api/public/mcp). ### Is the SHPBL: Repository Audit & Repair MCP server safe to use? SHPBL: Repository Audit & Repair scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm. ### What tools does the SHPBL: Repository Audit & Repair MCP server expose? SHPBL: Repository Audit & Repair exposes 17 tools: welcome, list_repos, method_protocol, run_contract, pin_source, and 12 more. Their descriptions and schemas cost roughly 8,234 tokens of context every time the server is loaded. ### Does the SHPBL: Repository Audit & Repair MCP server require authentication? No. We connected to SHPBL: Repository Audit & Repair without credentials and it answered, so anything it exposes is reachable by anyone who knows the address. ### Is the SHPBL: Repository Audit & Repair MCP server still maintained? SHPBL: Repository Audit & Repair is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced. ## Links - Remote endpoint: https://shpbl.com/api/public/mcp - Website: https://shpbl.com/mcp-access - Changelog RSS feed: https://verifymcp.io/servers/com-shpbl-repository-audit-and-repair/api-public-mcp.xml - Changelog JSON feed: https://verifymcp.io/servers/com-shpbl-repository-audit-and-repair/api-public-mcp.json - HTML version of this page: https://verifymcp.io/servers/com-shpbl-repository-audit-and-repair/api-public-mcp