Odel

AI & agents

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

12,843 servers6,859 publishers11 tags

All of AI & agents

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

Search verified agents and production agent-first AbsoluteJS packages.

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Lucent
@beepboop2025 · External

Call-scoped Clear Signing presentation checks for EVM signing agents.

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 Docker.Free to use.
MCP server: One MCP server.
Deep Agentic Core MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@deepagentlabs · External

Unified MCP server for AgenticLens and Agentic Chaos capabilities.

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 PyPI.Free to use.
MCP server: One MCP server.
DojoGenesis MCP
@dojogenesis · External

Practice library for coding agents: skill search/invoke, seed patches, scout, reflect, ADR writer

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 Docker.Free to use.
MCP server: One MCP server.
ProxyLLMRun by its publisher: served from their own domain, namespace checked by the registry.
@proxyllm · External

OpenAI-compatible LLM gateway: models, savings math, key provisioning, autonomous email-OTP signup

18% 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.
kcp-agent — KCP navigation plannerRun by its publisher: served from their own domain, namespace checked by the registry.
@cantara · External

Deterministic, fail-closed planner for KCP knowledge manifests: kcp_plan, kcp_load, kcp_validate.

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
kcp-harness — KCP compliance proxyRun by its publisher: served from their own domain, namespace checked by the registry.
@cantara · External

MCP compliance proxy between agent and tools: deterministic governance, fail-closed, audit trail.

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 npm.Free to use.
MCP server: One MCP server.
AI Agent Memory
@xiangzi1126 · External

Agent-agnostic persistent memory MCP server. Local-first: memories travel with your project.

5% 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.
MCP server: One MCP server.
LatAm Data
@svkbogislav · External

Latin American data for AI agents: tax-ID validation, indicators, FX, company lookups, holidays

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 PyPI.Free to use.
MCP server: One MCP server.
Corent
@gg13121 · External

Generate images, videos, voice, and text via the Corent API. Auto model routing with fallback.

6% 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 npm.Free to use.
MCP server: One MCP server.
Content Hooks
@closermethod · External

Short-form hook styles, script structures, retention and CTA rules for creators.

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

MCP server for an Asymptotic Ethics governance simulation with a verified compliance oracle.

3% 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.
MCP server: One MCP server.
SkillProofRun by its publisher: served from their own domain, namespace checked by the registry.
@skillproofdev · External

Check whether a Claude Code skill was tested and whether it works before installing it.

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Alertlogic
@rijul170 · External

MCP server for Alert Logic MDR — incident response, log search, SOAR, and SOC workflows

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 PyPI.Free to use.
MCP server: One MCP server.
Falcon
@rijul170 · External

Community extension of CrowdStrike falcon-mcp with near-complete Falcon API coverage

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.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
PLwC Personal
@mhoedt-ai · External

Windows x64/Python 3.12 MCPB preview: governed local tools and persistent profiles.

7% 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 MCPB.Free to use.
MCP server: One MCP server.
Claude Chat
@codechap · External

Anthropic Claude Messages API MCP server — chat, vision, web search, extended thinking

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 a package registry.Free to use.
MCP server: One MCP server.
Fable
@codechap · External

Anthropic Claude Fable 5 MCP server — top-tier planning and code critique for handoff

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 a package registry.Free to use.
MCP server: One MCP server.
Agent Hub
@blackaxgit · External

One MCP server bridging the Codex, Cursor, OpenCode, Claude, and Antigravity CLI agents

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.
MCP Blast-Radius Auditor
@aos-standard · External

Static blast-radius audit for MCP servers before agent install. Manifest optional.

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.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Tollbooth X402
@solomonisblack · External

Discover, quote, verify & self-check 56 x402 pay-per-call finance/tax calculators for AI agents.

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.
Pensieve
@praveen-ilangovan · External

Manually-triggered, self-organising personal memory for AI agents; SQLite, no vector DB.

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.
MCP server: One MCP server.
Boo MPP
@lucle87 · External

Pay-per-call crypto data for AI agents. USDC.e on Tempo via MPP. No API key.

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.
HPP x402 MCP BridgeRun by its publisher: served from their own domain, namespace checked by the registry.
@hpp-io · External

MCP bridge for autonomous x402 payments in HPP USDC.e — discover and pay for services per call.

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.

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