#governance

ProofLink MCP Server brings iTechSmart proof receipts, verifier access, accountability checks, and AI governance tooling to MCP-compatible agents.

Generates tailored AI governance frameworks for Australian businesses, aligned with the six AI6 practices in Australia's Voluntary AI Safety Standard (NAIC Guidance for AI Adoption). Profiles an organisation by industry, size and AI usage, then returns a structured, informational framework preview covering Accountability and Impact Assessment, with a link to the full six-practice framework. A structured starting point for Australian organisations shaping their AI policy and governance approach. Presents frameworks, not advice.

Shared control plane for AI coding agents — Claude Code, Cursor, Windsurf, and teammates sync tasks, persistent memory, decisions, and file locks through one MCP server. 12 consolidated tools (~15KB): task claim/release with resume packs, semantic memory search, lock policies & cost caps, approval workflows, automations with Slack/Discord alerts, live team console. Free tier: 2 agents, 100 tasks/mo. Setup: npx @doriku/cli setup

AgentValet is a governed credential broker for AI agents. It lets an agent call approved SaaS platforms through a proxy that checks permissions, holds sensitive actions for human approval, and records every call in an append-only audit log, so the agent never holds a raw token.

SaferAgenticAI MCP brings the Safer Agentic AI safety framework to coding assistants over the Model Context Protocol. It serves 238 normative implementation patterns and 14 operational heuristics across all 16 safety suites (9 Drivers + 7 Inhibitors) through 12 read-only tools: search patterns, resolve requirements, map a task to the relevant safety guidance, and follow cross-references.

Read-only MCP server for AI counsel research. Anteroom's tracked frontier-lab commercial commitments, safety-framework version history (RSP/PF/FSF), regulatory corpus, and partnership patterns, exposed as 5 tools. Every response is primary-source-cited. Not legal advice.

SaferAgenticAI MCP brings the Safer Agentic AI safety framework to coding assistants over the Model Context Protocol. It serves 238 normative implementation patterns and 14 operational heuristics across all 16 safety suites (9 Drivers + 7 Inhibitors) through 12 read-only tools: search patterns, resolve requirements, map a task to the relevant safety guidance, and follow cross-references.

Structured project memory for AI agents, delivered through a project-scoped remote MCP connector.

Marchward is an Apache-2.0 open-source runtime authority for AI agents. It routes an agent's tool calls through one control point: credential mediation (the agent holds a single Marchward key and never your real downstream credentials), an inference spend cap enforced before the call reaches the provider, human-in-the-loop approval gates on irreversible actions, and a tamper-evident hash-chained audit log. Public repo and packages are live (npm @marchward/*, PyPI marchward, official MCP registry ai.marchward/mcp-server), with a runnable governed-LangGraph example in the repo.

Post-quantum, tamper-evident receipts for consequential agent actions. Four tools (mint_action_receipt, mint_receipt_for_record_change, verify_receipt, audit_my_agent_inventory) signed Ed25519 + ML-DSA-65 (FIPS 204), verifiable offline from the certificate alone. Defaults to PQ-required verify mode (defends against Ed25519-only downgrade by requiring at least one verified PQ leg). Apache-2.0.

Shadow AI List is a maintained, risk-ranked registry of AI tools (the AI Exposure Index). This MCP server exposes 4 read-only tools: look up an AI tool's data-exposure risk, check whether a domain is a known AI tool (shadow AI on a network), browse tools by category, and get the highest-risk AI tools. No authentication; covers the free top 100. Remote endpoint: https://ailist.airiskmanagement.ca/mcp

EU AI Act compliance in your editor. Classify risk, cite obligations, draft Article 50 disclosures.

Public demonstration of MCPForge's MCP governance and security capabilities. Explore automatic OpenAPI-to-MCP conversion, Security Reports, Tool Quality Scores, risk classification, permissions, approval workflows, audit logs, credentials vault integration, and deployment readiness checks. Built to help teams evaluate MCP deployments before exposing production APIs to AI agents.

A read-only trust + intelligence layer between AI agents and your database — the agent never writes SQL, PII is refused before the query runs, and every call lands in a tamper-evident audit log. Postgres today.

Trust ratings for AI agents and websites. Look up an agent's reputation, scan a site's AI-trust-readiness, and verify signed scorecards in-band — reads are zero-auth. From Mnemom, the trust layer for the agent internet.

Governance middleware for AI agents — permission gates, human-in-the-loop approvals, compliance scanning across 8 frameworks, and hash-linked audit ledger. Hosted SSE endpoint, no self-hosting required.

X-ray your software architecture from any AI assistant: manage ArchiMate blueprints, score them against SOC 2, ISO 27001, GDPR, HIPAA and PCI-DSS, and pull generated code artifacts — all over MCP.

AI Governance Infrastructure for Microsoft 365. 24 MCP tools with policy enforcement, Need-to-Know compliance filter, revision-safe audit trail, and per-resource scope control. Deployed in your own Azure tenant — your data never leaves. DSGVO-first, EU AI Act ready.

Budget & cost control for AI agents: hard per-agent spend caps, rate limits, idempotency, and human-in-the-loop approval — enforced before each LLM call, not after the invoice. One hosted MCP endpoint (no proxy or self-hosting), settled via x402 (USDC on Base).

mcp-kinetic-gain is a single stdio MCP server that exposes all eleven Kinetic Gain Protocol Suite specs to any MCP-compatible client (Claude Desktop, Cline, Cursor, etc.) — 71 tools across AEO Protocol, Prompt Provenance, Agent Cards, AI Evidence Format, MCP Tool Cards, AI Tutor Cards, Student AI Disclosure, Classroom AI AUP, Clinical AI Disclosure, AI Incident Card, AI Procurement Decision Card, plus the DefenseTech 6-pack tooling shipped in v0.8.0. Includes ed25519 attestation verification, hash-chained audit-stream event composition and chain verification (offline AND live against a running audit-stream-py via the optional AUDIT_STREAM_URL env var), cross-spec drift detection, and a Decision Intelligence preview that generates a PolicyBundle from a Decision Card, infers rubric status, and plans incident remediation. Also doubles as a CLI: `npx mcp-kinetic-gain validate path/to/doc.json` auto-detects which Suite spec a JSON file belongs to and validates it against the same zod schemas the MCP tools use. No API key. No build step. Headline tools: aup_check_compliance, decision_card_validate, decision_card_to_policy_bundle, attestation_verify, suite_doc_drift, audit_chain_verify, audit_event_emit, audit_events_query, audit_chain_verify_live. Repo: https://github.com/mizcausevic-dev/mcp-kinetic-gain Suite: https://suite.kineticgain.com License: Apache-2.0

EU AI Act · APRA · NIST AI RMF · ISO 42001 · AU AI Safety — 6 tools, 53 resources, 5 prompts. Grounded compliance citations for any MCP client.

Governance firewall for autonomous AI agents. Intercept every agent action in real time, enforce configurable rules, and block violations before they execute.

Open scientific knowledge MCP for AI agents. Three profiles: search (15 tools incl. find_evidence, compare_papers, explore_topic), publish (5 tools for direct submission with AI-assisted review), govern (20 tools for proposals, voting, methodology shaping). Public Alpha. Apache 2.0.

Airtable is the database and operations layer for your agents — whether running product, marketing, sales, ops, HR, or a custom business app. It combines structured data with multiplayer visual surfaces (grid, kanban, calendar, gallery, timeline) humans and agents share — plus sync integrations to Jira, Salesforce, Zendesk, Google Drive, Databricks, and the rest of your stack, all backed by enterprise governance. This plugin makes Claude fluent in Airtable: creating bases and schema, working with records, and sharing UI for collaboration. Bundles the official Airtable MCP server.

Search and retrieve cryptographically-verified compliance nodes. 3,000+ nodes across 31 pillars AI Governance, Banking & Global Finance, Cybersecurity, Medical & Healthcare, Legal & IP Sovereignty, ESG and more. Zero hallucination: every node traces to primary legal sources with avg 7 citations.

Pre-execution enforcement and tamper-evident audit trails for AI agents. Hash-chained action logs, Ed25519 signatures, covenant policy language. EU AI Act Article 12 ready. Works with Claude Desktop, Cursor, VS Code.

ThumbGate is an agent governance MCP server that prevents costly AI mistakes before they execute. It provides pre-action gates, shared lessons across agents, and team-level safeguards for AI coding workflows. Features include Thompson Sampling for intelligent decision-making, feedback loops, and integrations with Claude, Cursor, and OpenCode.

Runtime policy enforcement for AI agents. Evaluate every agent action against your organization's policies before execution. Define policies once in the Hejdar dashboard, enforce everywhere via MCP. Supports observe mode (shadow/audit) and enforce mode (real-time blocking).

Make your AI agents cheaper, faster, and more reliable. 5 products, 14 MCP tools, 1 API key. Task deduplication, cost prediction, output validation, behavioral governance, and shared failure intelligence. Anonymous demo mode — try all tools without a key. 1,000 free credits/month, no card required. https://plith.ai/.well-known/mcp/server-card.json

5 APIs behind one MCP server: task deduplication (DedupQ), cost prediction (BurnRate), output validation (QualityGate), behavioral governance (GuardRail), shared failure intelligence (PitfallDB). No signup needed. 1,000 free credits/month.

Deterministic pre-action verdict gate for agent memory — USE/WARN/ASK/BLOCK before an agent acts on a stored memory. Governs your existing store, doesn't replace it.

Preflight validation before every AI agent action. Block hallucinations, stop drift, prove what's safe to act on. F1=1.000 across 239 corpus cases.

Adaptive security toolkit for AI agents. Assess inputs for prompt injection, scan outputs for credential/PII leaks, teach new attack patterns to semantic memory, harden prompts with role-lock and sandboxing, and monitor metrics — all locally via MCP. Zero false positives on benchmarks, 179 tests, Apache-2.0.

The guardian layer for AI agents. Scoped sessions with spend limits (Gate), AES-encrypted secrets (Vault), immutable audit trail with anomaly detection (Watch), and proxy mode that intercepts every MCP tool call for policy enforcement. Human-in-the-loop approvals, webhooks, 10 MCP tools, REST API. Works with Claude, Cursor, Windsurf, and any MCP client.

Stop re-explaining your codebase every session. Delimit is the universal governance layer for AI coding assistants — persistent memory, tasks, and policy enforcement that works across Claude Code, Codex, Cursor, and Gemini CLI. 180+ MCP tools across 5 domains: governance (lint, diff, policy, semver), context (memory, ledger, sessions, handoffs), shipping (deploy, publish, rollback, changelog), observability (metrics, logs, alerts, status), and orchestration (multi-model deliberation, agent dispatch, swarm triggers). Core capabilities: 27-type deterministic breaking change detection for OpenAPI specs. Policy enforcement with strict/default/relaxed presets plus custom YAML rules. Cross-model session continuity — switch between Claude, Codex, Gemini, and Cursor without losing context. Multi-model deliberation where AI models debate until consensus. Git hooks, CI gates, and pre-commit governance. Zero-config onboarding with auto-detection of frameworks, specs, and test suites. Free tier includes API governance, persistent ledger, zero-spec extraction, and project scanning. Pro adds deliberation, security audit, test verification, encrypted vault, deploy pipeline, and agent orchestration. Install: npx delimit-cli setup

Persistent memory, knowledge graph, governed actions, and runtime orchestration for AI agents. 107 tools. Works locally with zero-config SQLite(no API key needed) or connects to Novyx Cloud for the full surface. Install: uvx novyx-mcp

AI agents call LLMs, invoke tools, and hit APIs — but have no built-in way to cap spend. A single agent loop can burn hundreds of dollars before anyone notices. Cycles MCP Server gives any MCP-compatible agent a runtime budget authority: tools to check, reserve, spend, and release budget before and after every costly operation. Works with Claude Desktop, Claude Code, Cursor, Windsurf, and any MCP host. Supports per-tenant budgets, soft-landing caps, and automatic heartbeat for long-running operations.

EU AI Act compliance scanning for Python AI agents. 10 tools that scan, analyze, and fix compliance gaps across LangChain, CrewAI, AutoGen, OpenAI, and RAG pipelines. Checks 6 EU AI Act articles with HMAC-SHA256 tamper-evident audit trails. pip install air-blackbox-mcp. August 2026 deadline ready.

Enterprise AI Control Plane — governance layer between your AI applications and providers. Spend tracking, runtime guardrails, policy enforcement, budget limits, compliance readiness (SOC2/GDPR/HIPAA), and real-time provider health. Works with Claude, ChatGPT, Copilot, and any MCP-compatible client.

Deterministic risk governance for crypto trading agents. Answers "How much can I risk?" with policy level, max position size, leverage limits, and blocked actions — computed from 9+ real-time data sources (on-chain, derivatives, macro, sentiment). Supports BTC and ETH. One tool: get_risk_policy.

PR-native API governance for AI agents. Detects breaking API changes at merge time, scores blast radius, and blocks unsafe agent tool calls before production. Preflight check, risk scoring, Decision Spec v1.0.

Tamper-proof audit trail for AI decisions. Record, verify, and export cryptographic proof chains via MCP. 6 tools: proof_record, proof_verify, proof_chain_verify, proof_get, proof_export_jsonld, proof_public_verify.

Production MCP server giving AI agents metered access to live Hedera blockchain data. Query token prices, screen identities, monitor governance, write tamper-evident HCS compliance records, and analyze smart contracts — all paid in HBAR micropayments per call.

Cryptographic runtime governance for AI agents. 20 tools. Sealed policy artifacts, continuous measurement, tamper-evident proof. Ed25519 + SHA-256.

MCP server for agent-executable compliance documentation. Browse, assess, and implement Colorado AI Act (SB 24-205) deployer requirements directly from your AI agent. Tools: protocol listing, schema retrieval, compliance gap assessment, deployer classification.

Governance middleware for AI agents: deterministic policy enforcement, cryptographic audit trails with digital signatures, DLP/PII detection, Trust Score per agent (0-100), EU AI Act compliance (Art. 9, 11, 12, 14), Agent BOM generation, and Circuit Breaker. Native support for LangGraph, CrewAI, and AutoGen.

Governance and audit layer for MCP tool calls. TrustLoop intercepts every AI agent action, logs it to a tamper-evident audit trail, blocks unsafe tools via kill-switch, and anchors proof to the blockchain. Drop it into any MCP setup in minutes, no code changes required.

TEOS MCP is an MCP server that performs real-time diff-level security scanning for AI agents and CI/CD pipelines. It analyzes code diffs before merge or deployment and returns a deterministic gate decision: ALLOW WARN BLOCK Built for: • AI agents • Autonomous systems • DevSecOps teams • CI/CD workflows Features: • Diff risk scoring • Deterministic merge gate • Real-time enforcement • Usage-based monetization (pay-per-scan) • Optional on-chain verification Unlike gateway filters, TEOS MCP performs code-level intelligence before execution.

36 enterprise-grade MCP tools for AWS infrastructure, security compliance, AI workflows, agent governance, and operational resilience. Includes IAM policy validation with security scoring, MFA compliance auditing, CloudFormation/SAM template generation, DynamoDB single-table design, OAuth configuration validation, vector embedding generation via Amazon Bedrock, error pattern analysis, data lake readiness assessment, risk classification, task routing, 12 ACI governance tools for AI agent safety (decision classification, financial gates, compliance checks, blast radius estimation, rollback generation), and 4 local stakeholder interview tools that require no API key.

AI-Native Financial Network — Banking, trading, lending, governance & marketplace for autonomous AI agents. 120+ tools, real USDC/EURC, on-chain settlement.

Preloop is the MCP Governance Layer. Add approval gates to AI tool calls. Intercept risky actions, collect human decisions, and keep an audit trail.

Manage test cases directly from Claude, Cursor, Windsurf, and other MCP-compatible AI coding assistants. TestCollab serves as a governance layer and truth engine for AI-generated code - your test cases define what "correct" means, so when AI writes or modifies code, it has a clear source of truth to validate against. Features: • List test cases with filtering and sorting • Create new test cases • Update existing test cases • Pagination support for large test suites

The batteries-included, No-Code FinOps automation platform, with the AI you trust.

A Model Context Protocol (MCP) server that enables AI agents to interact with the Tally API, providing access to DAO governance data, proposals, and metadata. Built with TypeScript and GraphQL, it offers a secure and efficient way to fetch and sort DAO information through standardized MCP functions.