Governance firewall for autonomous AI agents. Intercept every agent action in real time, enforce configurable rules, and block violations before they execute. Works with any LLM or agent framework.
Cross-OEM industrial machine intelligence: identity, normalization, automation, attestation.
Agent discovery and cross-registry reputation for AI agents: semantic search over 15,000+ MCP servers and agents, reputation scores aggregated across registries, and tools to rate and look up agents before installing. No authentication required.
Standardized, restatement-aware SEC + European (ESEF) XBRL fundamentals, served to your agent.
Revnuvo MCP server for the agent economy. Tools: verify domains, resolve DNS, assess domain trust/risk, register agents, create tasks, submit results, verify task outputs, and get agent reputation leaderboard. The canonical developer home for the Revnuvo x402 ecosystem — SDK, Gateway, and Resource APIs is developers.revnuvo.site
tani (谷, "valley") is an agent-native hub. AI agents discover capabilities in a registry ranked by computed invocation trust — success rate, dependents and schema stability, earned by execution, never self-reported stars — exchange answers verified by execution, and find each other. tani-mcp puts the hub inside an agent's loop as 12 tools: resolve a capability by intent + constraints, describe a surface's schema/examples/failure-modes, discover and register agents, submit sur
Agent infra: email, phone, social, domains, VPS, wallets. Paid per-action via x402, no API key.
Live US options chains with Greeks and IV, a screener, SQL, and FMP fundamentals.
Bring your GFT (Git for Thought) white-box thinking map to any AI agent. 把你的思维脉络接给任何 agent。
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
Datasets for founders: directories, newsletters, and agencies, with metrics attached.
Deterministic AI code review, with an audit record. Governance inside the agent loop.
Onchain AI-agent reputation oracle on Base. Get a 0-100 score + SAFE/CAUTION/BLOCK verdict for any Base wallet, agent, token deployer, or x402 endpoint in <100ms — EIP-712 signed and verifiable onchain against the MainStreetVerifier contract. ERC-8004 + x402 + 19 MCP tools to preflight, verify, score, vet, and compare agents before you pay them. Free reads (100/day/IP); pay-per-call audits over x402 (USDC on Base).
Persistent code knowledge graph + 9 composite MCP tools for AI coding agents.
Read, validate and write e-invoices on your own machine. XRechnung, ZUGFeRD, Factur-X, UBL, CII.
# Vynix: Visual Website Feedback for AI Coding Agents Capture **visual website feedback** with **annotated screenshots**, **element inspection**, **browser annotations**, **DOM context**, **console logs**, **network requests**, and **AI-ready metadata**. **[Vynix](https://www.vynix.in/)** helps developers, designers, QA teams, product managers, agencies, and AI coding agents reproduce and fix bugs faster by turning visual feedback into structured, actionable reports. ## Fe
# Valuein **Audit-grade SEC fundamentals & smart-money data for AI agents** > Make investment calls your agent can defend — 30 years of point-in-time SEC fundamentals and institutional smart-money flows, every number traceable to the filing it came from. Valuein gives any MCP-compatible agent — Claude, Cursor, ChatGPT, Codex — the data a research analyst needs to reach a conclusion *and* defend it. One endpoint, two datasets, zero hand-waving. --- ## What your agent pull
Find, inspect and install reviewed reusable AI-agent capabilities from superskill.sh.
**AI-powered smart contract forge** with an 8-agent adversarial security audit system. ### Tools | Tool | Cost | |---|---| | `pentagonal_audit` — 8-agent security pen test | $5 | | `pentagonal_generate` — contracts from natural language | $5 | | `pentagonal_fix` — fix vulnerabilities | Free | | `pentagonal_compile` — Solidity → ABI + bytecode | Free | | `pentagonal_lookup` — token intelligence + honeypot detection | Free | | `pentagonal_rules` — self-learning security rules
OneHQ Commission Calculator MCP is a MCP server that gives AI assistants direct access to insurance commission calculation and compliance tools. It lets you model distribution hierarchies, calculate exact earnings per agent tier, validate structures against real carrier rules, and look up benchmark contract ranges — all without leaving your AI workflow. The OneHQ Commission Calculator MCP exposes 5 tools: 1. calculate_commission — Computes exact earnings per agent given an
Coherence guard for shared files: denies stale writes so agents don't silently overwrite each other.
Build on the Flarelink stack — Cloudflare auth, D1, and R2 — from your AI coding tools.
Verified-credit carbon offset clearinghouse — list, purchase, and retire conservation credits with proof of retirement; only credits with verification references are accepted. The conservation flywheel of the agent economy. Part of the Viridis Agent Fleet. Durable state, free to call. Genesis receipts: github.com/jdhart81/viridis-agent-fleet/blob/main/docs/GENESIS_RECEIPTS.md
Utilize advanced API capabilities to enhance your coding experience.
Validated registry of MCP servers, OpenAPI tools, and AI plugins. Continuously tested via live handshake, scored on rolling reliability metrics, and monitored for uptime. Query by status, score, or capability before your agent connects.
Search GitHub, npm, PyPI, StackOverflow, ArXiv from one MCP — built for coding agents.
Persistent AI memory layer for developers. Never re-explain your stack to AI tools again. Conxt captures your decisions, coding rules, preferences, tool choices, and workflows across Claude, ChatGPT, Gemini, Cursor, and Windsurf — and surfaces them automatically at the start of every new session. **8 MCP tools:** - [get_context](cci:1://file:///c:/Users/pgava/Projects/conxt-engine/conxt_mcp/tools.py:223:0-255:52) — load relevant memories for the current task - [get_memories
A colony of AI citizens: join with no credential, prove skills, earn, vote on the rules.
Agent-operated cold email infrastructure: domains, mailboxes, warmup, campaigns, replies over MCP. 17 tenant-scoped tools.
Check any Base wallet before you pay it. Free, no signup, no account needed.
# ShipStatic MCP **One URL. Your agent ships.** Drop `https://mcp.shipstatic.com` into any MCP client. Your agent can publish a website in its next message — **free, no install, no signup, no API key**. ## Hosted — no install ``` https://mcp.shipstatic.com ``` **Claude Code:** ```bash claude mcp add --transport http shipstatic https://mcp.shipstatic.com ``` **Cursor, Antigravity, Windsurf, n8n — anywhere with `mcp.json`:** ```json { "mc
Web search API for AI agents. Search the web and get structured results: title, URL, snippet, and metadata. Up to 10 results per query. Current news, documentation, research papers — everything indexed. Tools: web_search_query. Use this when your agent needs to find information, research topics, check current events, or verify facts. The fundamental research tool every agent needs. IMPORTANT: For deep fact-checking with evidence, use research_check_fact. Returns: {results:
One encrypted channel where Claude Code, Cursor, Codex and any other agent talk to each other.
Build, test and run iOS apps on a remote Mac from any machine. XcodeBuildMCP-compatible tools.
Agent Commerce Protocol MCP — bridges Stripe ACP + Google AP2 + Coinbase x402 for agent payments
Local agent wallet + 900 pay-per-call data APIs — free discovery, x402 USDC, code-level spend caps