Odel

AI & agents

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

12,705 servers6,739 publishers11 tags

All of AI & agents

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
AION SUPREME Agent Temple
@wisemankonstantin-droid · External

Verified agent routing with bounded discovery, outcome evidence and economic policy.

14% 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 8 Oct.Free to use.
MCP server: One MCP server.
AgentResolver — Agent Commerce Health Monitoring
@waxsway · External

Free API/MCP/x402 health checks plus $19 hourly managed monitoring for agent services.

7% 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.
VibeView
@vibeview · External

Drive cloud iOS, Android, Apple TV, Android TV and Roku devices to verify app changes.

6% 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 npm.Free to use.
MCP server: One MCP server.
Agenttoll
@tevfikefeaydin · External

21 paid data tools plus free quote/budget inspection, with bounded USDC payments on Base.

7% 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 npm.Free to use.
MCP server: One MCP server.
MCP Output Firewall
@tangfei7777-cell · External

Three-layer firewall for MCP: content, egress and action policy. Proxy or server.

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
ContextPullRun by its publisher: served from their own domain, namespace checked by the registry.
@mi2arun · External

Exact document sections on demand for LLM agents: index in context, search, read, grep, neighbours.

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.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Agent Resort
@ktwspecial-lab · External

AI agent vacation game with challenges, badges, passports, status, Palm Points and leaderboard.

5% 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.Free to use.
MCP server: One MCP server.
Xestando
@javyxx · External

Spanish SME suite: VeriFactu invoices, time clock, e-sign. AI drafts; you approve.

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.
Automan
@i02202 · External

Autonomous AI agent selling pay-per-call skills settled with x402 micropayments (USDC).

6% 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.
MemoStem
@girapphe · External

Your reviewed knowledge, across AI conversations.

5% 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.Free to use.
MCP server: One MCP server.
HallucC — Hallucination & Safety Guardian
@fredyee · External

Fact-check LLM outputs with cited sources. API key: aihcc.cloud/keys.

19% 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.
Education Scope MCP
@yama-tana · External

Classify Japanese curriculum scope, audit grade limits, and search normalized MEXT data.

2% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.Free to use.
MCP server: One MCP server.
DVERA CT verification tools
@suresofttechnologies · External

DVERA drives CT verification of mission-critical C/C++: setup, analysis, tests, coverage.

4% 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 MCPB.Free to use.
MCP server: One MCP server.
Small PrintRun by its publisher: served from their own domain, namespace checked by the registry.
@smallprint · External

Check an MCP server, skill or plugin before your agent uses it: tool text on record, changes graded.

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Forge Arena — Agent WildsRun by its publisher: served from their own domain, namespace checked by the registry.
@timeprooflabs · External

Autonomous agents create, compete, converse, vote, and build reputation in a bounded public world.

4% 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.Free to use.
MCP server: One MCP server.
Live UK Company Search
@macaroonnetwork · External

Search current public UK company metadata from the official Companies House Public Data API.…

17% 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 PyPI.Free to use.
MCP server: One MCP server.
CoralSwarm ConnectRun by its publisher: served from their own domain, namespace checked by the registry.
@coralswarm · External

Search and save your coding work in a CoralSwarm ocean: sessions, decisions, meetings.

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; you sign in with your account.Free to use.
MCP server: One MCP server.
tashanRun by its publisher: served from their own domain, namespace checked by the registry.
@tashan · External

Check any MCP server or agent skill before installing: upkeep, real adoption, and OSV advisories.

7% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
CrierRun by its publisher: served from their own domain, namespace checked by the registry.
@crier · External

Bulletin board for agents: find and post local events, offers and requests. Reads need no key.

4% 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.Free to use.
MCP server: One MCP server.
RobotBase on-chain data MCP (BTC / XMR / ZEC)
@wygogogo19 · External

Read-only MCP for BTC, ETH, XMR and ZEC: fees, nodes, p2pool, shielded pools.

4% 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.
DiversZ Commons
@parkschun79 · External

MCP tool window for autonomous AI: principles, join, talk, treasury, signal.

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; no sign-in.Free to use.
MCP server: One MCP server.
Devpick
@kimbobmarley03 · External

43 local developer tools for AI agents: PDF, subnet, regex, JSON, conversion, and more.

6% 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 npm.Free to use.
MCP server: One MCP server.
Governance
@coderifts · External

Signed, offline-verifiable contract-change authorization. Only a granted change can proceed.

5% 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.Free to use.
MCP server: One MCP server.
Deadlatch
@diabloluo · External

Local advisory pre-trade risk gate for agents. Never places orders.

4% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.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