"Open Collective" matching MCP servers:

Open-source permission control plane for AI agents — scan, enforce, and audit every tool call with code-level policies that prompt injection can't bypass.

Enables agents to search and call the full OPNsense core and plugin API, perform model-validated CRUD and settings operations, and use curated firewall, service, and network tools with optional auto-revert writes.

Enables AI-driven open-source intelligence investigations by exposing 30 tools for scanning emails, usernames, domains, IPs, and more, with real subprocess execution.

Open-source guardrails between AI agents and FHIR clinical data — PHI redaction, immutable audit, step-up auth, tenant isolation. MCP server + OpenAI/Gemini adapters. A healthclaw.io project.

An open experience layer for conversational AI - routes user intent into safe, consented, stateful experiences.

Security-focused MCP server for TP-Link Omada Open API workflows, enabling network management via natural language.

Deterministic agentic data firewall that secures, monitors, and controls AI agent interactions with data and software via MCP, preventing data leaks.

Open-source MCP proxy that enforces security policies, content scanning, and audit logging between AI agents and tool servers

Official MCP server built into Casdoor, the open-source identity and access management (IAM) and single sign-on (SSO) platform. It exposes Casdoor's users and applications as MCP tools over a JSON-RPC endpoint at /api/mcp, with per-tool authorization driven by OAuth scopes, and can also act as an MCP gateway that proxies and authorizes agent access to upstream MCP servers.

MCP server that verifies proof-bound consequential execution at the edge, acting as the open trust anchor for the Actenon ecosystem. It validates PCCB proofs without issuing grants or making policy decisions.

Open-source MCP servers that give AI agents structured access to networking standards, device databases, and security data.

Enables MCP-compatible AI coding agents to retrieve shared skills, project architecture maps, vault secret statuses, handoff checkpoints, external MCP definitions, and code audit results on demand across multiple IDEs. It reduces context tokens and supports secure, cross-agent task continuity.

Enables AI agents to inspect, check, and audit signed offline spending authorizations, and to issue hash-chained receipts for each action taken against them. Enforces per-transaction, total, expiry, merchant, and human-approval constraints, returning allow, needs_human, or deny with the specific failing constraint.

Enables read-only access to personal European bank accounts through Enable Banking, allowing MCP clients to list accounts, retrieve balances, search and summarize transactions, and estimate spending with bounded, privacy-preserving tools.

Enables users to list their open GitHub pull requests and verify their identity through Keycard-backed, short-lived tokens while connecting via Claude Code.

Connects your Bradescard account to AI assistants via Open Finance Brasil, enabling natural language queries about balances, statements, credit card bills, and investments in read-only mode.

An open-source MCP server that protects AI agents at runtime by evaluating every tool call against YAML policies and generating audit trails.

Open-source scanner that finds authorization logic embedded in application code. Precision-first static analysis with per-language rule packs, externalization percentage and per-finding confidence; generates OPA/Rego policy stubs. Apache 2.0, no telemetry.

Open-source security tools for coding agents. Provides dependency advisory audits and structured evidence for remediation through a local stdio MCP server, with optional hosted security tools.

Open-source MCP server: encrypted local keys and state, operator approval gates, a hash-chained log.

Enables read-only access to Brazilian Open Finance banking data through Pluggy, allowing queries of accounts, balances, transactions, card bills, category spending, and connection status.

IntentFence is an open spend and action policy gate for autonomous AI that evaluates tool call constraints like scope, cost, data-retention, and approval, returning decisions such as safe_to_proceed, needs_review, or denied, and provides an MCP server endpoint at /mcp.

An open-source implementation of the Model Context Protocol (MCP) that bridges AI agents with enterprise systems, enabling secure access to real-world data and capabilities.

Real security scanners for AI coding agents — SAST (441 rules), secret detection (419+ patterns), dependency CVEs (OSV.dev), MCP/skill vetting, MITRE ATT&CK. Open-source, Rust, free

MCP server for querying Google's Open Source Vulnerabilities (OSV) database. Enables vulnerability lookups by package, version, commit, or ID using natural language via Pipeworx gateway.

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

BrowseWeave enables MCP-compatible AI clients to control and read web pages already open in a real browser, providing semantic views and screenshots as needed.

Enables AI agents to securely use Open Agent ID credentials for signing requests, looking up agent data, and exchanging encrypted messages. It performs all cryptographic operations within the server process to ensure private keys are never exposed to the AI agent.

Enables AI agents to invoke tools over a mutually authenticated TLS endpoint, with server-side certificate and identity checks plus fail-closed per-tool authorization through Open Policy Agent.

Turns an OpenAPI specification into a broker-published slot of curated, LLM-ready tools that a human operator reviews, tests, and approves before anything goes live. The resulting tools are declarative and run under the broker's authorization, audit, execution limits, and secret handling.