$ loading_
Pins approved MCP manifests and skill files to content addresses, blocking tampering.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "pin-the-protocol" yet — see the docs or source repo.
Verify approved MCP tool manifests at the gateway and block any modified descriptions before they reach model context.
Returns verification results and blocks tampered tool descriptions from entering context.
Pin approved skill files to content addresses and رفض loading if the content changes.
Provides a content-addressed reference that prevents silent replacement of skill files.
Before sending third-party tool descriptions to the model, verify they match the approved version.
Confirms integrity or blocks mismatches, reducing prompt-injection risk.
Developers or DevOps teams can verify MCP manifests against approved versions before connecting multiple tools. This reduces the risk of tampered descriptions or prompt poisoning reaching model context.
When teams distribute AI skill files, they can pin them to content addresses so later loads always reference the same content. This is useful for change-sensitive internal skill packs.
Verify third-party tool descriptions before they enter the model to keep untrusted text out of context. This fits security-focused workflows and supply-chain trust requirements.
It is a verifying MCP gateway that pins approved tool manifests and skill files to content addresses. Its goal is to block tampered descriptions before they enter model context.
The provided information only says it works with an MCP gateway and content-address pinning; no specific installation or runtime requirements are given. For details, see the source repository.
A regular gateway mainly forwards requests, while this one adds verification and pinning: it binds approved content to content addresses and blocks loading when tampering is detected.
Analyze Linear dependencies to find the ticket unlocking the most downstream work
Score trust and safety before installing MCP servers, AI skills, or npm packages.
Give MCP-compatible AI clients real context for Pinoox PHP HMVC projects.
Publish, author, and reuse AI tools and skills via MCP and REST.
Create, verify, and manage cryptographically verifiable AI agent identities via MCP.
Local MCP tools for AI agents to parse, verify, and hash credentials.