"How to build your own knowledge base" matching MCP servers:

Open-source AI governance toolkit. MCP servers & CLIs for scanning, auditing, and managing your AI environment

Enables verifying that recorded build accesses stay within a declared closure by inspecting and verifying hash-only receipts, without executing builds or making network requests.

Provides a per-person MCP interface to a knowledge graph of legal matters, enforcing OPA-based access barriers and logging every request in a hash-chained audit trail.

Let AI agents act for a person on websites, with the person's approval on their phone. The agent's browser runs in a sandboxed vault it cannot read into; when a site asks for a password, CAPTCHA or 2FA, the owner takes over from their phone.

An MCP server that sends plain-text Gmail messages only to a predefined allowlist, using generated recipient IDs instead of email addresses to enforce security.

Enables agents to perform Schnorr zero-knowledge identification and cryptographic attestation through a native MCP interface, including commitment-challenge-response proofs, JWT validation, Merkle inclusion checks, and replay protection.

Enables cryptographic chunk hashing, reverse claim-to-source attribution, clearance boundary validation, and provenance audit trails for enterprise knowledge graphs to combat hallucinations.

Enables agents to ground claims in enterprise knowledge by hashing source chunks, tracing claims back to their origins, validating clearance boundaries, and maintaining audit trails to support anti-hallucination workflows.

Enables local zero-knowledge encryption of a personal vault and sanitization of PII such as credentials, credit cards, and addresses before dispatch to cloud LLMs, with client-side rehydration of masked data.

Autonomously introspects an undocumented SQLite database to expose auto-generated CRUD tools, join-explaining prompts, and schema resources for LLM agents. All queries run through pre-validated parameterized SQL templates, so the model never writes or sees raw SQL, with full audit logging of every operation.

This MCP server autonomously introspects SQLite databases to auto-generate CRUD tools and join prompts, while enforcing zero-knowledge security through pre-validated SQL templates.

Enables agents to encrypt and sanitize sensitive data such as credentials, credit card numbers, and addresses locally before dispatching prompts to cloud LLMs, then rehydrate the masked values client-side. It runs deterministically with zero external dependencies over MCP JSON-RPC stdio, so no plaintext PII leaves the user's machine.

Enables AI agents to access only task-relevant data with secrets hidden and personal details pseudonymized, while enforcing destination policies to prevent data leakage even under prompt injection.

Enables EVTX (Windows Event Log) analysis via Hayabusa, providing tools to scan event logs and retrieve detection rules.

Offline MCP server that checks and scans your own AI prompts and outputs against a local compliance rule corpus. Returns rule ID, severity, citation, and remediation per finding — no API key, Apache 2.0.

Share encrypted, self-destructing secrets from your AI agent. Zero-knowledge E2E encryption. Agent-blind input sources (env:, file:, dotenv:) keep secrets out of LLM context.

MCP server that integrates Apache Ranger authorization with RAG, enforcing Ranger policies to control access to knowledge bases before forwarding queries to RAG Studio.

Hand a secret to another agent as an encrypted, pay-per-read token delivered exactly once, leaving no copy behind. Also pre-flights an x402 endpoint before your agent pays it. Runs locally over stdio and encrypts in your own process, so there is no hosted version to hand your plaintext to.

Enables MCP-compatible agents to query security checklists, protocols, and framework mappings to safely build and operate AI agents, with tools for checklist runs, protocol lookup, mapping lookup, and threat search.

Enables production-grade answer verification for LLM agents by independently re-checking answers with a configurable verifier model, enforcing confidence policies, and producing Ed25519-signed, auditable verification results with optional web search and knowledge-base evidence.