delx-protocol
7657davidmosiah/delx-witness-protocol
MCP server Claude CodeCodexCursor +2
Free agent continuity MCP: resume after compaction, warm handoff, recover from failure. No key. Remote server at api.delx.ai.
38,601 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
davidmosiah/delx-witness-protocol
MCP server Claude CodeCodexCursor +2
Free agent continuity MCP: resume after compaction, warm handoff, recover from failure. No key. Remote server at api.delx.ai.
Skill Claude CodeCodex
Audit any MCP server for agent-readiness — get a 0–100 score across 10 checks with the exact fixes. Local-first, zero credentials.
dbsectrainer/mcp-agent-trace-inspector
MCP server Claude CodeCodexCursor +2
Step-by-step observability for MCP agent workflows. Runs locally from the mcp-agent-trace-inspector npm package. Needs 1 environment variable to run.
dbsectrainer/mcp-cost-tracker-router
MCP server Claude CodeCodexCursor +2
Real-time cost awareness for MCP agent workflows. Runs locally from the mcp-cost-tracker-router npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
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.
MCP server Claude CodeCodexCursor +2
A registry of 5,900+ peer-authored skills any MCP agent can search and load on demand. Runs locally from the skilldb npm package.
MCP server Claude CodeCodexCursor +2
Safe scheduled AI agents with governance gates. Verified, receipted, fail-closed. Runs locally from the dingdawg-loop npm package. Needs 1 environment variable to run.
Cursor rule Cursor
PSX Repotector guards this repo. Handshake FIRST and say who you are — every crossing is logged in a visitor register. No deep tool answers until you handshake.
MCP server Claude CodeCodexCursor +2
One universal Voyager: name a goal; it activates senses (repo, net) and runs a live mission. Runs locally from the @dir-ai/voyager-agent npm package.
MCP server Claude CodeCodexCursor +2
Per-call paid skills for AI agents, run server-side: inputs in, outputs back. The body never ships. Runs locally from the sealed-mcp npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server for the Fail Modes taxonomy — a knowledge base of AI system failure modes. Runs locally from the failmodes-mcp npm package.
MCP server Claude CodeCodexCursor +2
Emergence Science SDK: Verifiable Agreements for the Agent Economy. Runs locally from the @emergencescience/mcp-server npm package. Needs 1 environment variable to run.
enrichgateagent-png/beacon-mcp
MCP server Claude CodeCodexCursor +2
Search 17,900+ open-source AI agents by capability, ranked by GitHub traction. Free, no key. Runs locally from the beacon-mcp npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
Zero-config MCP security scanner for AI-generated apps. 25K+ vulnerability patterns. Remote server at mcp.frogeye.ai.
MCP server Claude CodeCodexCursor +2
MCP server for portable reputation and skills passports across Africa. Runs locally from the sifa-mcp Python package.
MCP server Claude CodeCodexCursor +2
Carry your Phaedo cognitive fingerprint into any MCP client: style injection + decision consults. Runs locally from the phaedo-mcp npm package.
Skill Claude CodeCodex
The step-by-step safe workflow for editing a live Genudo agent's instructions: load the current text, write the local pipeline mirror, stage the edit, show a before/after diff, get explicit confirmation, push, then record the outcome. Use before any updatepipeline or updatestage call that changes persona…
Skill Claude CodeCodex
Standing infrastructure for agents via DataSieve (x402, Base). Use when a task needs anything to happen while no agent is running — a dead-man switch before long/risky autonomous work, a cron/schedule that fires webhooks, watching a web page or an on-chain condition (whale transfers, price crossings, wallet activity)…
MCP server Claude CodeCodexCursor +2
Trust Graduation gate: Claude can do real work once Mission decides what it is allowed to do. Runs locally from the @gomission/mcp npm package.
MCP server Claude CodeCodexCursor +2
Peer-to-peer, end-to-end-encrypted collaboration channel for AI coding agents over MCP. Runs locally from the covalent-bond npm package. Needs 3 environment variables to run.
MCP server Claude CodeCodexCursor +2
AI compliance obligations across EU AI Act, ISO 42001, Colorado AI Act, NIST, HIPAA, SOX, FTC. Runs locally from the @governmyai/mcp-server npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
AI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts. Runs locally from the @gsep/mcp npm package. Needs 4 environment variables to run.
hrishikesh-thakre/ai-workbench-mcp
MCP server Claude CodeCodexCursor +2
Goose-first acceptance, validation, routing, and audit layer for agentic work. Runs locally from the ai-workbench-mcp Python package.
MCP server Claude CodeCodexCursor +2
Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools. Runs locally from the agentstack-mcp npm package.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: