Odel

AI & agents

Memory, payments and tools for AI agents, other agents to work with, and gateways to more tools.

13,023 servers6,999 publishers11 tags

All of AI & agents

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
Intent-Verified Development (IVD)
@leocelis · External

33 tools that make AI write, implement, and verify intent against explicit, testable constraints.

8% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.A remote server; it needs your API key.Free to use.
MCP server: One MCP server.
TrustBenchRun by its publisher: served from their own domain, namespace checked by the registry.
@lithvall · External

x402 provider rankings + Ed25519-signed payment receipts + signature verification (3 tools).

4% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Maqui Analytics
@luis-fuentes · External

Marketing analytics for local businesses — Instagram, ads, web traffic, SEO and reviews.

9% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
Nullcone Threat Intelligence
@maco144 · External

Real-time threat intel for AI agents: 890K+ IOCs incl. prompt-injection & AI-skill threats

10% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Stargate
@junct-bot · External

Stargate - 42 tools for cross-chain transfers and bridge data

10% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.The endpoint has not answered since 9 Oct.Free to use.
MCP server: One MCP server.
humanMCP Marketplace — federated listings across personal MCP servers
@kapoost · External

Federated listings from personal humanMCP servers. Search offers, trades by humans.

5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
AgentCrush
@kristof-sudo · External

Market intelligence for the AI agent economy: rankings, trust signals, liveness. 13 tools.

4% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Agent Loop Detector
@lazymac2x · External

Cloudflare Workers MCP server: agent-loop-detector

4% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Agent Memory
@lazymac2x · External

Cloudflare Workers MCP server: agent-memory

5% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
K-Work Trust
@hycore220 · External

Korean business record validation and workflow safety gates for AI agents.

8% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Aiaam
@javierfajardo85-rgb · External

MAI-1 registry: search 100+ verified AI tool contracts with live reliability scores in one call.

10% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.The endpoint has not answered since 12 Oct. The repository is archived.Free to use.
MCP server: One MCP server.
GoldHoldRun by its publisher: served from their own domain, namespace checked by the registry.
@jerrysrodz · External

Persistent memory for AI agents. Search, store, and recall across sessions.

8% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
Handoff
@josephibra · External

Durable agent-to-agent handoffs and shared scratchpad for multi-agent workflows.

9% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; it needs your API key.Free to use.
MCP server: One MCP server.
Shadowgate
@josephibra · External

Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.

11% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; it needs your API key.Free to use.
MCP server: One MCP server.
Aarna
@junct-bot · External

Aarna - 34 tools for swap quotes, liquidity pools, and trading data

8% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.The endpoint has not answered since 10 Oct.Free to use.
MCP server: One MCP server.
MCP GSC CPG
@gsc-em · External

A2A MCP & CPG Rails: HBPC (Hygiene + Beauty Personal Care) procurement and ESG.

16% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.A remote server; no sign-in.The endpoint has not answered since 12 Oct.Free to use.
MCP server: One MCP server.
Norric
@gucceed · External

Swedish B2B intelligence for AI agents: insolvency risk, procurement, BRF health and more.

5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Indian Regulatory Data
@guptaprakhariitr · External

SEBI orders, RBI notifications, MCA filings, NSE/BSE announcements, AMFI NAV.

9% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.The endpoint has not answered since 11 Oct.Free to use.
MCP server: One MCP server.
Agent Signals
@hassanahashish-design · External

Hiring, SEC, research papers, GitHub & Hacker News as JSON for AI agents. Pay-per-result on Apify.

9% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; it needs your API key.Free to use.
MCP server: One MCP server.
Hvilkenai
@erorund · External

Daily Scandinavian AI benchmark — Norwegian, Swedish, Danish. 12+ models tested.

3% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
CacheBash
@feelgreatfoodie · External

Let your AI sessions talk to each other — messaging, tasks, sessions, and alerts

9% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
Giskard Memory
@giskard09 · External

Pay-per-use semantic memory for AI agents. SHA256 commitment, Ed25519 sig, Lightning.

14% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.The endpoint has not answered since 7 Oct.Free to use.
MCP server: One MCP server.
Mission — Trust Graduation Gate
@gomission · External

Trust Graduation gate: Claude can do real work once Mission decides what it is allowed to do.

13% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.A remote server; no sign-in.Deprecated by the publisher: Security update required. Upgrade to @gomission/mcp@0.2.3 (stable) or @gomission/mcp@0.3.0-beta.3 (beta). These older versions have receipt access vulnerabilities; affected proxy versions also have consequential-action classification flaws. See https://github.com/gomission/mcp/blob/main/SECURITY.md. The endpoint has not answered since 10 Oct.Free to use.
MCP server: One MCP server.
Connector Platform
@danielsalles · External

100+ pre-built SaaS integrations for builder apps. Multi-tenant, scoped per end_user.

8% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.Free to use.

More topics

Sales & customersMarketing & advertisingShopping & e-commerceBusiness financePersonal finance & investingLegal & governmentSecurity & privacySoftware developmentCloud & IT operationsData & webWork & productivityCommunicationDocuments & writingDesign & mediaNews & informationScience & researchHealth & fitnessEducation & careersTravel & placesHome & propertyEntertainment & hobbiesIndustry & transport