SHPBL: Repository Audit & Repair

Open a pull request (Practitioner)

write_to_repo

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. 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/<run-seal>/LEDGER.md — the folded ledger for one run.
.shpbl/<run-seal>/REPORT.html — the branded report, if one was produced.
.shpbl/<capability-name>/ — 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 - <name> — <what it fuses> — <why neither part sufficed>. 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. Give each kept capability a one-line contract in .shpbl/README.md, in the form - <name> — <path> — <contract>. That index is what makes the library reusable: on the next run, read it and pass those entries as own_library to evaluate_repo, fix_repo or run_gauntlet, and the run will tell you which concerns you already solved before citing anything new. Those entries stay yours — they are held for the call and never stored by SHPBL. Repairs are the exception: write the repaired file at its own path, never under .shpbl/.

Input Schema

TableJSON Schema

Name	Required	Description
`key`	No	Your SHPBL subscription key (shpbl_mcp_…). Optional if your client sends it as the `Authorization: Bearer …` request header.
`kind`	No	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 missing. `foundry` means built software and its tests, landing under `.shpbl/` beside the index the same way a harvest does — only ever an artifact whose Build Intent `build_intent` authorised. `repair` means fixed files at their own paths, and nothing is scaffolded.
`repo`	Yes	The GitHub repository to write to: `owner/repo` or a URL.
`files`	Yes	Complete file contents to commit. For a repair, the whole fixed file — not a diff.
`title`	Yes	Pull request title — say what the change does.
`branch`	No	Branch to write on. Defaults to one derived from `run_id`, or `shpbl/<date>-<n>`; reusing a name appends to that PR.
`run_id`	No	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. Prefer this over `branch`.
`summary`	Yes	Pull request body: the repair order, or the run seal and coverage of a harvest. Markdown.
`base_ref`	No	Branch to open against. Defaults to the repository's default branch.
`github_token`	No	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.
`build_authorization`	No	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 refuses to land an artifact it never gated.

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only supply hints; the description carries the behavioral burden and does so thoroughly. It discloses that nothing is pushed to the default branch, that auth can be a SHPBL key plus GitHub App or a one-off token, that the server never reads repos the caller has no right to read, that composites stay private, and that build artifacts are only landed with signed authorization. This far exceeds the annotation hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but well structured: the core action is front-loaded, followed by auth, then file placement, then the library index contract, then the repair exception. It earns most of its length given 11 parameters and complex privacy/build rules, though some points are reiterated from the schema, such as full contents rather than diffs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the operational essentials: auth, repository selection, branch/run_id behavior, file placement, privacy boundaries, and build authorization. With no output schema, it could have named the return value, such as the PR URL or number, but for a complex write tool the description is otherwise comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description adds real semantic value beyond the schema: it clarifies that files must be full new contents rather than diffs, that run_id/branch reuse updates the same PR, that repository choice must never be assumed, and that repairs write outside .shpbl/. It does not individually elaborate every parameter, but it complements the schema meaningfully.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action and resource: "Land finished work in a repository as a pull request" and explains that passing full file contents opens a branch and PR. It clearly distinguishes this write/PR-creation tool from read-oriented siblings such as evaluate_repo or list_repos by emphasizing the PR outcome and the 'nothing pushed to default branch' guarantee.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear usage context: use it to land finished work via a PR, pass full new contents rather than diffs, and let a human review and merge. It also provides concrete guidance such as 'ask which one, or call list_repos first; never assume' and 'Repairs are the exception'. It does not explicitly enumerate when not to use this tool versus each sibling, but the operational context is strong.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All SHPBL: Repository Audit & Repair tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0

Disambiguation4/5

Most tools target distinct stages or resource types: evaluate/fix/harvest are clearly separate audit phases, and write_to_repo/list_repos are unambiguous. The library_* trio is mostly separable but library_document and library_index both offer access to volumes, and run_gauntlet partially overlaps the individual stage tools, so a couple of boundaries are less crisp.

Naming Consistency4/5

Names are uniformly lowercase snake_case and mostly follow a verb_noun pattern: evaluate_repo, fix_repo, harvest_repo, write_to_repo, list_repos, run_gauntlet. A few are noun_noun or resource-prefixed like library_search, library_document, subscription_status, and welcome/selfcheck_mcp are one-offs, so it is predictable but not perfectly uniform.

Tool Count5/5

At 14 tools the server sits within the ideal 3-15 range, and each tool has a plausible role in the audit/repair, library, or operational workflow. The count is on the larger side but justified by separate free and Practitioner lanes, library services, and health/status checks.

Completeness4/5

The core audit lifecycle is well covered: list/scope, evaluate, fix, harvest, write back, plus library search and run orchestration. The main gap is that build_intent explicitly gates COMPOSE/SPECIALIZE/CREATE operations, but no actual compose/specialize/create tools are exposed, and there is no explicit run_gauntlet cancellation or reset, though agents can work around both.

Resources

Need Help?