Repository audit & repair · MCP
One endpoint. Connect the chatbot you already use — Claude, ChatGPT, Cursor, Codex — and it can survey any repository, repair what the survey finds, and harvest the whole tree into a sealed capability ledger. This server does the deterministic work and hands back the method, so the only model in the loop is the one you are already talking to.
1 · Add the endpoint
https://shpbl.com/mcp
This door speaks OAuth. Your client registers itself, opens a sign-in page, and you approve it once — no key is ever typed into a client or a prompt.
2 · Sign in and bind your key once
Signing in proves who you are; it does not prove what you bought. Bind your subscription key to your account at your account and every agent you connect afterwards carries your tier automatically. Stage one needs none of this — the free tools answer any caller.
3 · Client cannot sign in? Use the key-only door
https://shpbl.com/api/public/mcp
Authentication None, transport Streamable HTTP, plus one request header: Authorization: Bearer shpbl_mcp_YOUR_KEY. Same twelve tools. If your client cannot send headers either, pass the key as the tool's optional key argument.
Is it working?
Paste your key once. This page checks it exactly as the tools do and answers in one line: tier, status, calls used this month, and whether pull requests are switched on.
Stage One
Evaluate
Free — no key
evaluate_repo
The repository as it actually is: file and byte counts, language spread, the spine files to read first, and the risk signals the tree gives up on its own. Then the evaluation protocol your agent carries out.
Stage Two
Fix
$29/mo · Practitioner
fix_repo
A repair order for the files you name, ranked by what fails silently first, with unified diffs to apply, the guard that should catch each fault next time, and what was left alone and why. Your agent writes the repairs; you approve every change.
Stage Three
Harvest
$79/mo · Governor
harvest_repo
The whole tree in stable batches, with the harvest protocol, the eight component classes, the six verification axes and a citable run seal. Your agent folds a capability ledger you can inherit from.
Stage All of it
Run the gauntlet
$79/mo · Governor
run_gauntlet
One tool that conducts the whole method the way the downloadable kit does: survey, a library comparison before the work starts, the evaluation, the repair order, the full batched harvest, a second library comparison against what you harvested, the branded HTML report, then the pull request and the contribution path. One call to plan it, one call per step to walk it.
Replace OWNER/REPO with the repository, or ask your agent to call list_repos and pick from the list. Paid stages page their material: tell your agent to walk every part before it concludes.
Every fact on this page is published in one machine-readable file. Paste this to your assistant and it connects itself:
Read https://shpbl.com/llms.txt and connect to the SHPBL MCP server described in it, then explain in plain language what it can do for me.
Claude.ai (web or mobile)
Settings → Connectors → Add custom connector
Sign-in door (recommended)
URL https://shpbl.com/mcp
Auth OAuth — Claude registers itself and asks you to sign in
Key-only door
URL https://shpbl.com/api/public/mcp
Auth None
Transport Streamable HTTP (under Advanced)
Under “Request headers” press Add header:
Header name Authorization
Value Bearer shpbl_mcp_YOUR_KEYClaude Desktop / Claude Code
Settings → Connectors, or claude_desktop_config.json
{
"mcpServers": {
"shpbl": {
"url": "https://shpbl.com/api/public/mcp",
"headers": { "Authorization": "Bearer shpbl_mcp_YOUR_KEY" }
}
}
}ChatGPT
Settings → Connectors → Add → MCP server
Name: SHPBL URL: https://shpbl.com/mcp (OAuth — you sign in once) Client cannot sign in? Use the key-only door: URL: https://shpbl.com/api/public/mcp Auth: none Header: Authorization: Bearer shpbl_mcp_YOUR_KEY
Cursor
.cursor/mcp.json in your project, or Settings → MCP
{
"mcpServers": {
"shpbl": {
"url": "https://shpbl.com/api/public/mcp",
"headers": { "Authorization": "Bearer shpbl_mcp_YOUR_KEY" }
}
}
}Codex / any MCP client
Add a remote server of transport type “streamable HTTP”
url = "https://shpbl.com/mcp" # OAuth
transport = "http"
# or the key-only door:
# url = "https://shpbl.com/api/public/mcp"
# headers = { Authorization = "Bearer shpbl_mcp_YOUR_KEY" }Evaluate · Free — no key
“Use the SHPBL MCP server to evaluate github.com/OWNER/REPO, then follow the protocol it returns.”
Fix · $29/mo · Practitioner
“Use the SHPBL MCP server's fix_repo to repair the findings in github.com/OWNER/REPO. My key is set as a request header, so call it without a key argument. Walk every part, then give me the repair order, the diffs and the guards.”
Harvest · $79/mo · Governor
“Use the SHPBL MCP server's harvest_repo on github.com/OWNER/REPO. My key is set as a request header, so call it without a key argument. Walk every batch in order, carry the ledger forward, then restate the run seal.”
Run the gauntlet · $79/mo · Governor
“Use the SHPBL MCP server's run_gauntlet on github.com/OWNER/REPO. My key is set as a request header, so call it without a key argument. Start with no step to get the run card, walk every step in order, then close the run and give me the HTML report.”
Evaluate · Evaluate
Free
No key required
Point your agent at any public repository and get the survey, the signals, and the evaluation protocol. No key, no card.
Practitioner · Fix
$29/mo
5,000 calls / month
Repair what the evaluation found. The verbatim source of the files you name, with the remediation protocol your model works to.
Governor · Harvest
$79/mo
50,000 calls / month
Harvest the whole repository into a sealed capability ledger — every batch, every class, every verification axis, cited.
On a paid key, install the official SHPBL GitHub App on the repositories you choose and the tools can open pull requests instead of handing you text to copy. Nothing is ever pushed to your default branch.
Paste your key in the field above first.
github_token on the call instead — used once, never stored — or simply hand you the diffs.