Odel

AI & agents

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

12,844 servers6,860 publishers11 tags

All of AI & agents

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
BranddockRun by its publisher: served from their own domain, namespace checked by the registry.
@branddock · External

Give your agent your brand's DNA: context, F-VAL validation and on-brand content generation.

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

Marketplace where AI agents get real work handled and build provable, evidence-only reputation.

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.
Nexez Agentic Commerce
@nexez · External

Find Nexez sellers, inspect offers, and validate checkout or negotiation before buyer approval.

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.
Agentgates MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@agentgates · External

Confidential compute and inference sold to agents over x402 USDC, plus an agent wallet over MCP.

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

Coding agents run multi-leg cross-chain DeFi. Legs re-derived from your sentence before signing.

12% 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.
Agent Arcade Protocol 5Run by its publisher: served from their own domain, namespace checked by the registry.
@agentarcade · External

AI-only game publishing, autonomous play, live observation, replay and independent certification.

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; no sign-in.The endpoint has not answered since 11 Oct.Free to use.
MCP server: One MCP server.
vrsaiRun by its publisher: served from their own domain, namespace checked by the registry.
@vrsai · External

Machine-native capabilities with explicit contracts and machine-readable commerce.

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.
Sichta WebRun by its publisher: served from their own domain, namespace checked by the registry.
@gigliotti · External

Check whether AI agents can read any website: 18 deterministic checks, each with its fix.

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 13 Oct.Free to use.
MCP server: One MCP server.
x402 Text Tools CatalogRun by its publisher: served from their own domain, namespace checked by the registry.
@tunnelmole · External

Pay-per-call NLP & embeddings APIs on Base via x402. No keys/signup; agents pay per call in USDC.

16% 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 13 Oct.Free to use.
MCP server: One MCP server.
Agent ArenaRun by its publisher: served from their own domain, namespace checked by the registry.
@agentarena · External

Agents play Connect 4, Battleship and duels for real USDC. Every move published. First match free.

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.
Blue Cap Machine CommerceRun by its publisher: served from their own domain, namespace checked by the registry.
@soundiq · External

Deterministic MCP utilities, validation, evidence verification, and x402 commerce on Base.

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; no sign-in.Free to use.
MCP server: One MCP server.
KortexRun by its publisher: served from their own domain, namespace checked by the registry.
@rohnelt · External

Which x402 service actually works: uptime, valid 402, and settlements proven on-chain.

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.The endpoint has not answered since 8 Oct.Free to use.
MCP server: One MCP server.
Yaktool
@yaktool · External

73 local deterministic tools: GTIN, feeds, CSV-XLSX, Digital Link QR, e-invoices. Rules cited.

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
SCRIPTMASTERLABS — SqueezeOS MCP
@scriptmasterlabs · External

SqueezeOS MCP for live machine discovery and x402-paid USDC APIs on Base.

12% 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.
RESET VerificaRun by its publisher: served from their own domain, namespace checked by the registry.
@resetparatodos · External

Deterministic Mexican/LatAm verification + sanctions & PEP screening for AI agents. Pay via x402.

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.
HexaRun by its publisher: served from their own domain, namespace checked by the registry.
@hexahq · External

Shared company knowledge, workflows, and connected apps for the AIs your team already uses.

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.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
Nexus Agent Network · AlpineLead OI
@maxschnee74-source · External

Nexus Agent Network: AI agent marketplace for MCP, A2A orchestration and machine payments.

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; no sign-in.Free to use.
MCP server: One MCP server.
Echo Sentiment — XLM Market Sentiment
@mikedorian375 · External

XLM (Stellar) market sentiment for agents — keyless, pay-per-call via x402 (USDC on Base).

22% 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.
Commentary ReviewRun by its publisher: served from their own domain, namespace checked by the registry.
@commentary · External

Human-owned review for agent plans, rendered documents, Forms, research, and live previews.

6% 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.
Sigistry Plugin & Skill CatalogRun by its publisher: served from their own domain, namespace checked by the registry.
@sigistry · External

Search verified Claude Code plugins and skills; fetch portable SKILL.md sources. Read-only.

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.
Saymon RU Data APIRun by its publisher: served from their own domain, namespace checked by the registry.
@payforapi · External

Russian company lookup (EGRUL/INN), Cyrillic search, RU page to Markdown. Pay per call in USDC.

6% 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.
Plumbline — a trust layer for LLM answersRun by its publisher: served from their own domain, namespace checked by the registry.
@lattice-sys · External

Every figure re-checked against SQL-computed facts; unsupported questions refused with the reason.

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.
ScoreIA Open ChamberRun by its publisher: served from their own domain, namespace checked by the registry.
@scoreia · External

Test your AI agent over MCP in the Open Chamber: a timed public trial with signed cards.

6% 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.
AgentMeshRun by its publisher: served from their own domain, namespace checked by the registry.
@agentmesh · External

Be an agent on the AgentMesh network: find agents, hire them, be hired, and read your mesh inbox.

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.

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