Superlog
An open-source agent that observes & fixes your application. Query logs, traces, metrics, incidents.
An open-source agent that observes & fixes your application. Query logs, traces, metrics, incidents.
Agent-first task marketplace MCP — discover, claim, and deliver paid workspace tasks.
Let your agent hire humans or other agents, and be hired. Post jobs, take bids, pay on completion.
Free SEO, GEO, and AEO audits: analyze any page or domain, AI-crawler access, agent readiness.
Promote your app or software with UGC creator videos. Agent drafts the campaign, a human funds it.
Pre-deploy ship gate AI agents call before shipping. Also audits the agent's own MCP config.
Agent-first e-signature MCP server with **offline PAdES signing** and hash-chained audit. The same 19 tools / 4 prompts / 12 resources are reachable via stdio (`npx @drbaher/sign-cli mcp serve`) for local agents and over HTTP for remote ones. **Architectural claim:** an LLM agent can drive every step of a contract workflow except the actual signing gesture, which stays gated behind a human via per-signer approval tokens (TTL-bounded, scoped to one email, single-use). Pre-sig
A powerful web crawling MCP server built for autonomous AI agent swarms. It provides high-speed, parallel web data extraction, allowing distributed multi-agent systems to seamlessly harvest real-time web intelligence. Scale your swarm’s automated research capabilities with optimized, structured web data delivery built directly for LLM tool use.
Read-only MCP server for public wallet and portfolio analytics by [PerpStats](https://perpstats.com). Give an LLM agent a public wallet address and get back portfolio passport, risk score, transactions, DeFi exposure, and NFT breakdown — across Ethereum, Polygon, BSC, Arbitrum, Optimism, Base, Solana, and Bitcoin. ## Tools - **wallet_overview** — total USD value, top assets, chain allocation. Up to 5 addresses per call. - **portfolio_health_score** — explainable 0–100 score
Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.
Chronary — calendar-as-a-service built for AI agents. Give your agent its own calendar: create and manage calendars and events, find meeting times across multiple participants, run multi-party scheduling proposals, place auto-expiring holds, set availability rules, receive webhooks, and sync external iCal feeds. One API key, 47 MCP tools, no OAuth — calendaring and scheduling infrastructure purpose-built for autonomous agents and copilots. Chronary works with Claude, Cursor,
MCP-native co-founder directory your AI agent searches, screening inbound pitches for you.
Search companies, enrich contacts, and reveal emails and phones from your AI agent.
AI agent website builder. Create and publish link-in-bio sites via MCP or REST API.
AI agent hosting platform: 37+ connectors, 181 tools, BYOK vault, marketplace.
Document hosting and encrypted agent memory with multi-tenant persistence.
Multi-agent LLM security layer detecting prompt injection and jailbreaks.
Route one agent through one MCP server to many, with progressive tool discovery to shrink context.
Search the Couchbase documentation from your MCP client via a hosted documentation agent.
Evidence-backed architecture-quality analysis for Python agent applications.
Ophir protocol tools for AI agent discovery, negotiation, and settlement
The agent never writes SQL: queries compile from a semantic layer you control, PII refused first.
Sandboxed shell exec for MCP clients: run untrusted agent commands in a gVisor container.
Agent-native product catalog: 300M+ products across US+SEA. Search, compare, deals.
Persistent decision memory for agents — learns which action works in which context
Manage your entire social media operation from your AI assistant. Swonkie is a social media management platform: connect it and your agent can pull analytics, track competitors, write and schedule posts, run them through team approval, and publish, across Facebook, Instagram, LinkedIn, TikTok, YouTube, X, Threads, Pinterest and Google Business Profile. ## What your agent can do - **Analytics** — daily and per-post metrics for any connected profile, with metric discovery per
Architecture guardrails for AI-written code: dependency graph, impact, dead code, CI gate
—
**Buy My Agent** — discover AI agents by outcome. A read-only MCP server over the public marketplace catalogue. Search and read public listings; no purchase, subscribe, or account actions. **Tools** - `search_agents` — natural-language search of the catalogue - `get_agent` — one listing's full public details - `list_agents` — browse listings (optional category filter) - `list_categories` — the marketplace categories
Hosts AI-generated web content (HTML, images, SVG, JSON) at a public URL, with custom domains.
ToolHail is the discovery-and-payment layer for AI agents. **find_mcp_server** (free) searches every major MCP registry and returns ranked, ready-to-use servers for a plain-language task. **call_tool** (paid) proxies and meters a call to any remote MCP server via Stripe — with a spend cap, an egress allowlist, and a per-call execution receipt. Find and use the tool your agent is missing, without installing anything.
Governance, x402 quote, evidence receipt and cross-border preflight for A2A/MCP agent workflows. Covers EU, Japan, India, Korea, Singapore, Brazil/LGPD, Nigeria/NDPA, South Africa/POPIA. Returns ALLOW/REVIEW/BLOCK verdict with blocked fields, SCCs required, and signed evidence receipts. x402 micropayments on Base mainnet. No autonomous outreach, no settlement.
Communication stack for AI agents: SMS, AI voice calls, phone numbers, and account events.
Check AI crawler robots.txt policy and monitor public-site policy, sitemap, and llms.txt changes.
AI-powered MCP server for searching and conversing over FHIR R4 clinical documents. Features hybrid retrieval (BM25 + pgvector), cross-encoder reranking, LangGraph multi-agent workflow, PII masking, and multi-provider LLM support (Ollama, OpenAI, Anthropic, Bedrock). 15+ tools for agent queries, document retrieval, session management, and embeddings ingestion.
Give your agent grounded access to your SIGNLD workspace: your connected business systems, your Knowledge Graph, and your Decision Topics. Instead of guessing at your numbers, the agent reads your actual data, runs read-only SQL over it, and answers Knowledge-Graph-first, so every answer maps back to the real entities and metrics in your business. It can also turn a query into a chart, save a shareable dashboard, and help build out the Knowledge Graph itself.