Odel

AI & agents

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

12,667 servers6,708 publishers11 tags

Most popular in AI & agents

By GitHub stars, at most two per publisher
  1. Number 1: World Monitor@worldmonitor/mcpLive markets, conflicts, country risk, chokepoints, energy, and China decision signals. 93 tools.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.88,201 GitHub stars.
  2. Number 2: REA@morluto/reaReverse engineer anything from your terminal or agent with one CLI and MCP server.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.77,747 GitHub stars.
  3. Number 3: Claude Flow@ruvnet/claude-flowAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.73,814 GitHub stars.

Tags in AI & agents

MCP gateways & tool hubs6,610Agent & MCP directories2,260AI agent governance1,857Agent collaboration1,657AI memory1,223Agent payments1,148LLM access & routing896AI evaluation & benchmarks752Prompt & context management647Code execution sandboxes307Chatbot building255

All of AI & agents

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
AIHawk
@feder-cr · External

AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.

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

Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search

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.
Agent Skills Search Server
@mcp · External

Search and discover Agent Skills from the skills.sh registry. Powered by HAPI MCP server.

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.The endpoint has not answered since 11 Oct.Free to use.
MCP server: One MCP server.
OpenWork MCP GatewayRun by its publisher: served from their own domain, namespace checked by the registry.
@openworklabs · External

Your OpenWork org's skills, plugins, workflows, and connections through one OAuth MCP URL.

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.
screenpipe
@screenpipe · External

Search your local screen recordings, audio transcripts, and computer activity from screenpipe.

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.
FunASR
@modelscope · External

Transcribe local audio with FunASR and SenseVoice using private, on-device inference.

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 Docker.Free to use.
MCP server: One MCP server.
Coder
@coder · External

Manage Coder workspaces, templates, and cloud development environments

3% 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.
MCP server: One MCP server.
MCP Toolbox for Databases
@googleapis · External

MCP Toolbox for Databases enables your agent to connect to your database.

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 Docker.Free to use.
MCP server: One MCP server.
MCP Toolbox for Databases
@googleapis · External

MCP Toolbox for Databases enables your agent to connect to your database.

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 Docker.Free to use.
MCP server: One MCP server.
OpenMetadata
@open-metadata · External

Official OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.

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 a package registry.Free to use.
MCP server: One MCP server.
ApifyRun by its publisher: served from their own domain, namespace checked by the registry.
@apify · External

Extract data from any website with thousands of scrapers, crawlers, and automations on Apify Store ⚡

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; it needs your API key.Free to use.
MCP server: One MCP server.
PraisonAIRun by its publisher: served from their own domain, namespace checked by the registry.
@mervinpraison · External

AI Agents Framework with Self Reflection and MCP support

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 PyPI.25 known advisories (OSV) in its package.Free to use.
MCP server: One MCP server.
Honcho
@plastic-labs · External

Memory that reasons: continual learning for stateful agents. Better context, fewer tokens.

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.
MCP Registry Server
@mcp · External

Publish and discover MCP servers via the official MCP Registry. Powered by HAPI MCP server.

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-Native Brain
@builderio · External

Cited company knowledge from Slack, meetings, transcripts, and decisions

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; you sign in with your account.Free to use.
MCP server: One MCP server.
Agent-Native Chat
@builderio · External

Minimal chat-first app with durable threads, actions, and the app-agent loop

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; you sign in with your account.Free to use.
MCP server: One MCP server.
basebalance.cloud — x402 RPC & MCP gatewayRun by its publisher: served from their own domain, namespace checked by the registry.
@basebalance · External

USDC-gated Base JSON-RPC: free 10 req/min, $0.50 per 10k. Failover, cache, /mcp, ledger.

40% 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.
OuroborosRun by its publisher: served from their own domain, namespace checked by the registry.
@q00 · External

Pins an acceptance spec; the verify command and expected output never enter the success contract.

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

MCP server for progressive tool usage at any scale (see https://klavis.ai)

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; it needs your API key.Free to use.
MCP server: One MCP server.
Ask Jev
@pollinations · External

Evaluate state with typed choice, score, and probability questions.

Not assessed yet.What it can do is not assessed yet.A remote server; it needs your API key.Free to use.
MCP server: One MCP server.
Connected Apps
@pollinations · External

Read Gmail, search GitHub, update Sheets, and post to Slack through Composio.

Not assessed yet.What it can do is not assessed yet.A remote server; it needs your API key.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