Search

prosemeter MCP server — deterministic prose scoring and the agent revise/converge loop over MCP

Grant-gated MCP tool calls: middleware enforcing AGP grants and proofs on Streamable HTTP tools/call requests.

RuntimeAI IDE integration — MCP server and CLI for Cursor, VS Code, and Claude Code

MCP server for investigating Datadog logs with an interactive MCP Apps UI and shareable HTML reports

Local MCP (stdio) server for Redmine. Work with issues, projects and time entries from any MCP client.

MCP server exposing the Orly database as conflict-free shared memory for AI agents

E2E-encrypted chat for Claude users: MCP client, relay server and business bots

MCP provider for the Clue Defect Recorder

An MCP server that captures the rationale behind code changes at the moment they are written, binding decisions to commits with full provenance, and serves that context later without guessing. It records 'why code exists' and tracks anchor health over time.

Delegates mechanical text-to-text tasks to a local LLM to save Claude subscription quota, reading files server-side so large content never enters Claude's context.

Enables AI agents to coordinate on a shared repository using commutativity-proven parallel landing and regenerative merge, avoiding rebase conflicts through symbol-level leases.

MCP server that enforces governance on agentic decisions with auditable evidence records, providing tools for understanding, calibrating confidence, and navigating handoffs based on policy.

A workflow-level MCP server for Vikunja with a fixed task pipeline (Backlog → Queue → Design → Build → Review → Done) that enables agents to claim, advance, and comment on tasks, while handling human callbacks and blocked items.

For the harness-agnostic integration pattern that this plugin implements, see [docs/reference-pattern.md](../../docs/reference-pattern.md). This README covers Claude Code-specific behavior layered on top of that shared route/report pattern.

MCP server for Sites.Reviews — give Claude, Cursor & any AI assistant a website's trust score, real user reviews and scam-check signals before you trust or pay it. Domain reputation & due-diligence for AI agents.

MCP server for multi-agent review with Compare and traceable receipts

npm wrapper for the CodeScry local codebase index CLI and MCP server

Deterministic, self-hosted AI agent memory for TypeScript apps via MCP, HTTP sidecars, and the Vercel AI SDK

Launch Claude Desktop in a sandbox environment via Docker

Aarmos adapter for the Model Context Protocol (MCP). Brokers MCP tool calls under Aarmos policy and writes AVAR receipts. Scheme: mcp://<name>/<tool>