Odel

AI & agents

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

12,924 servers6,936 publishers11 tags

All of AI & agents

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
Humanaway
@seankim-android · External

MCP server for humanaway, a social network for AI agents.

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 npm.Free to use.
MCP server: One MCP server.
Negotiate
@sanjana-pier39 · External

Negotiate prices at any negotiate.v1 store. AI shopper tools for Claude.

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.
Standup from your activity
@sathvic-kollu · External

Generate your daily standup from real GitHub, Jira, Linear, and Slack activity.

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.
Sayba AI Agent Social PlatformRun by its publisher: served from their own domain, namespace checked by the registry.
@saybanet · External

AI Agent social network with 23 MCP tools for social, tasks, skills, and XC token economy.

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.
Sayba Skill Market
@saybanet · External

Discover, invoke, publish, and rate AI Agent skills on Sayba platform

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.
OceanBus
@ryanbihai · External

Register, discover, message, and transact with other AI agents on the OceanBus network.

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.
SNHP — negotiation rules your AI can't break
@ryuxik · External

Turn a seller's offer into negotiation rules and draft replies to buyers inside them.

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

Read-only MCP server for the OPERANT AI operating-agent calibration benchmark.

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.
junai Pipeline MCP
@saajunaid · External

Agentic pipeline orchestration MCP server for AI-driven development 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.
Sable Platform + HyperDX Observability
@sable-inc · External

Manage Sable AI voice agents, query HyperDX logs and metrics, and deploy — all from your IDE

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 a package registry.The repository is archived.Free to use.
MCP server: One MCP server.
Modelcostsaver
@sachinuppal · External

Offline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network.

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.
MindForgeRun by its publisher: served from their own domain, namespace checked by the registry.
@sairam0424 · External

Read the MindForge engine over MCP: knowledge graph, project health, and audit log.

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.
Cycles — Budget Authority for AI AgentsRun by its publisher: served from their own domain, namespace checked by the registry.
@runcycles · External

Runtime budget authority for AI agents — reserve, enforce, reconcile spend across providers

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.
darwin-memo
@rogermsc · External

Self-curating agent memory kept honest by survival-based selection over measured outcomes.

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 PyPI.Free to use.
MCP server: One MCP server.
Sentinel Execution
@rohith1125 · External

AI-controlled algorithmic trading engine exposing 40 MCP tools across 9 namespaces.

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

138-tool MCP server for AI agent firms: security, A2A, Hebbian memory, fleet mgmt

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.
VivariumRun by its publisher: served from their own domain, namespace checked by the registry.
@rongchang726-png · External

A science game for AI agents: tune, infer, or out-evolve a living world, judged on held-out seeds.

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

Drop-in spend governance + cross-agent dedup proxy for AI agent fleets, with x402 settlement.

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.
Askew x402
@rubix1138 · External

DeFi yields, staking routing, semantic research & security intel via x402 micro-payments on Base

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 8 Oct.Free to use.
MCP server: One MCP server.
Perf
@rog0x · External

Benchmark, memory, Big O analysis for AI 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 npm.Free to use.
MCP server: One MCP server.
Testing
@rog0x · External

Test generation, mocks, coverage analysis for AI agents

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

AI-agent commerce: find products, mint tracking links, publish posts, earn commission.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Adaptive Memory Graph
@raskolnikovdd · External

Persistent memory for Claude via weighted, interconnected knowledge nodes.

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.
Aichat
@rcgalbo · External

Inter-agent communication for multi-agent Claude Code 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 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