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.
Agentwork
@ferm-ai · External

Official MCP server for Agentwork — delegate tasks to AI agents with human-in-the-loop

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.The endpoint has not answered since 7 Oct.Free to use.
MCP server: One MCP server.
Fintel Discovery — Financial Intelligence for AI Agents
@findimitrov · External

Delivers public regulatory and market data from 11 key sources such as FINRA, SEC, Census, FRED

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.
Claudetest
@fasteningcode · External

Playwright & Appium test automation for Claude. Generate tests, diagnose failures, open fix PRs.

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Elias MCP Sample Server
@elpadev · External

A sample MCP server for testing

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.
Agent Utility API
@eamondidier-ux · External

x402 pay-per-call tools: company enrichment, PDF extraction, Amazon/KDP data, YouTube transcripts.

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.Free to use.
MCP server: One MCP server.
Engrm
@dr12hes · External

Shared memory across devices, sessions, and agents for OpenClaw, Claude Code, and Codex.

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.
AiPayGent — Claude AI Tools
@djautomd-lab · External

Claude-powered AI tools: research, write, code, analyze, translate, debate, pitch, score, and more.

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 10 Oct.Free to use.
MCP server: One MCP server.
Elesync
@darknodebros · External

Private local-first AI workspace for shared context, knowledge, tasks, and memories

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 PyPI.Free to use.
MCP server: One MCP server.
Swarm Tips — Earn, Spend, and Discover for AI Agents
@corsur · External

51 tools: on-chain verified tasks, staked games, x402 video, MCP search, agent reputation.

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.
Velora LATAM Tools
@crossi-dev · External

Argentina CUIT/CUIL validation and AFIP fiscal QR generation. Pure, no-auth MCP tools.

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.
Deskbrid
@coe0718 · External

Linux automation. 125 MCP tools: windows, input, screenshots, clipboard, print, AT-SPI. 9 DEs.

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 Docker.Free to use.
MCP server: One MCP server.
Context Lens
@cornelcroi · External

Semantic search knowledge base with serverless LanceDB. Zero setup, 100% local, 25+ file types

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.
Vettly
@code-with-brian · External

Content moderation for AI applications. Moderate text, images, and video with configurable policies.

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.Runs on your machine, installed from a package registry.Free to use.
MCP server: One MCP server.
CloudBees Unify MCP Server
@cloudbees · External

Connect AI agents to CloudBees Unify: feature flags, CI/CD, release orchestration, and security

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.
Civis
@civis-labs · External

Structured knowledge base for AI agent solutions. Search, explore, and retrieve build logs.

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; no sign-in.Free to use.
MCP server: One MCP server.
Hipocampo MCP
@carrasquelalex1 · External

Bilingual dual memory with SSC for AI agents. Semantic search, embeddings, profiles.

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.
Aicoreutils
@caseshy · External

JSON-first Coreutils CLI for AI agents. 114 commands with sandbox, dry-run, and MCP support.

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.
Brains
@brainsforai · External

Personal wiki and memory layer for AI assistants. Persistent, structured memory across sessions.

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.
Braintrust
@braintrustdata · External

AI evaluation and observability platform — query experiments, logs, datasets, and prompts.

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.
Watchdog
@bountyyfi · External

MCP security proxy - detects and blocks 40+ MCP attack classes. Zero config.

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 PyPI.Free to use.
MCP server: One MCP server.
Vynn
@beee003 · External

Self-improving AI workflows with backtesting, prompt optimization, and scheduling

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.
AWS MCP Server
@aws · External

AWS MCP Server lets AI securely access AWS using docs, API calls, and SOP workflows.

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 PyPI.Free to use.
MCP server: One MCP server.
Ecommerce Command Center
@atul0016 · External

Daily ecommerce revenue, inventory, listing, shipping, and restock operations intelligence.

20% 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.
Unified Ad Intelligence
@atul0016 · External

Cross-platform ad spend, attribution, true ROAS, budget, and anomaly intelligence.

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.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