agent governance mcp servers

halofyai/halofy

MCP server Claude CodeCodexCursor +2

MCP server "halomem", hosted remotely, as configured in halofyai/halofy.

ucsandman/DashClaw

MCP server Claude CodeCodexCursor +2

MCP server "anythink" as configured in ucsandman/DashClaw. Launched with dotnet run --project C:/Projects/anythink-cli/mcp -- --profile dashclaw.

ucsandman/DashClaw

MCP server Claude CodeCodexCursor +2

MCP server "repowise" as configured in ucsandman/DashClaw. Launched with repowise mcp C:/Projects/DashClaw --transport stdio.

ucsandman/DashClaw

MCP server Claude CodeCodexCursor +2

MCP server for DashClaw governance — guard, record, invoke, and discover capabilities. Runs locally from the @dashclaw/mcp-server npm package. Needs 3 environment variables to run.

dengyier/OpenWorkProof

MCP server Claude CodeCodexCursor +2

Agent work contracts and verifiable execution protocol — Ed25519-signed, offline-verifiable proof-carrying work for AI agents. Runs locally from the openworkproof Python package.

saivedant169/AegisFlow

MCP server Claude CodeCodexCursor +2

MCP server "aegisflow" as configured in saivedant169/AegisFlow. Launched with bash scripts/mcp-stdio-bridge.sh.

vaaraio/vaara

MCP server Claude CodeCodexCursor +2

Accountable Autonomy for AI agents under the EU AI Act: policy-gated tool calls, hash-chained tamper-evident audit trails with external time anchoring, and independently verifiable attestation plus execution receipts per MCP tool call. Runs locally from the vaara Python package.

vaaraio/vaara

MCP server Claude CodeCodexCursor +2

Accountable Autonomy for AI agents under the EU AI Act: policy-gated tool calls, hash-chained tamper-evident audit trails with external time anchoring, and independently verifiable attestation plus execution receipts per MCP tool call. Runs locally from the vaara Python package. Needs 2 environment variables to run.

nerviq/nerviq

MCP server Claude CodeCodexCursor +2

Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.

getaxonflow/axonflow-claude-plugin

MCP server Claude CodeCodexCursor +2

MCP server "axonflow", hosted remotely, as configured in getaxonflow/axonflow-claude-plugin.

VamsiSudhakaran1/release-gate

MCP server Claude CodeCodexCursor +2

AI agent release decision engine - readiness scoring, regression gate, eval runner, trace validation, and evidence packs for CI/CD. Runs locally from the release-gate Python package. Needs 1 environment variable to run.

neurarelay/relay-action-card

MCP server Claude CodeCodexCursor +2

Govern proposed Action Cards with Decision Receipts before developer-owned execution. Remote server at www.neurarelay.com.

ericlovold/sanction

MCP server Claude CodeCodexCursor +2

The wallet an AI agent carries — mandate, budget, vault, and audit. Counterparties verify first. Runs locally from the sanction-mcp npm package. Needs 3 environment variables to run.

joinwell52-AI/FCoP

MCP server Claude CodeCodexCursor +2

stdio MCP server for the FCoP Python library: exposes the fcop package's Project, task, report, issue, GAL alert, and audit APIs to MCP clients (Cursor, Claude Desktop, …). Optional bridge, not a second protocol; depends on fcop 3.x, FastMCP, websockets. Runs locally from the fcop-mcp Python package. Needs 1…

KeyArgo/custodian-codex-guard

MCP server Claude CodeCodexCursor +2

MCP server "custodian-codex-guard" as configured in KeyArgo/custodian-codex-guard. Launched with custodian-codex-guard-mcp.

marchward/marchward

MCP server Claude CodeCodexCursor

Runtime authority for AI agents: credential mediation, spend cap, approval gates, audit log. Runs locally from the @marchward/mcp-server npm package. Needs 2 environment variables to run.

chrbailey/promptspeak-mcp-server

MCP server Claude CodeCodexCursor

Pre-execution governance for AI agents. Intercepts MCP tool calls before execution with deterministic blocking, human-in-the-loop holds, and behavioral drift detection. Runs locally from the promptspeak-mcp-server npm package.

Runestone-Labs/gatekeeper

MCP server Claude CodeCodexCursor

Run MCP tool calls through Runestone Gatekeeper — policy enforcement, human approval, audit. Runs locally from the @runestone-labs/gatekeeper-mcp npm package. Needs 4 environment variables to run.

denial-web/agent-immune

MCP server Claude CodeCodexCursor

Adaptive threat intelligence for AI agent security — semantic memory, multi-turn escalation, output scanning, rate limiting, and prompt hardening. Runs locally from the agent-immune Python package.

rtahabas/gatewards-sdk

MCP server Claude CodeCodexCursor

Drop-in spend governance + cross-agent dedup proxy for AI agent fleets, with x402 settlement. Runs locally from the @gatewards/mcp-server npm package. Needs 2 environment variables to run.

andreas-altamirano/mcp-governance-proxy

MCP server Claude CodeCodexCursor

MCP server "mcp-governance-proxy" as configured in andreas-altamirano/mcp-governance-proxy. Runs locally from the mcp-governance-proxy Python package.

rmichaelthomas/liminate-mcp

MCP server Claude CodeCodexCursor +2

Help your AI agent author the Agreements that govern it. Runs locally from the liminate-mcp Python package.

christian140903-sudo/agent-invariants

MCP server Claude CodeCodexCursor +2

MCP server "agent-invariants" as configured in christian140903-sudo/agent-invariants. Runs locally from the agent-invariants npm package.

christian140903-sudo/postcondition-mcp

MCP server Claude CodeCodexCursor +2

Outcome verification for AI agents. Declare what should change, observe the world independently, and issue hash-chained receipts. Runs locally from the postcondition-mcp npm package. Needs 1 environment variable to run.