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.
Agent Residue Evidence
@fantasyce · External

Report local task-scoped test and build residue without cleaning resources.

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 MCPB.Free to use.
MCP server: One MCP server.
Labnana MCP
@exoticknight · External

Generate and edit images with Labnana through a local MCP server with MCP Apps previews.

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.
Connect
@bvenkata · External

Protocol- & auth-agnostic API connector: SOAP/REST behind any auth, config-driven. Lib/API/MCP.

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.
NightMarquee
@ant-dev-lab · External

Cinematic website prompts plus demo footage, tuned for Lovable, Bolt, Cursor, Claude and Codex.

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.
autorouter
@webb-ventures · External

An MCP capability router: one search tool instead of every server's tool schema.

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.
MCP Light Memory
@peterpirog · External

Local-first persistent memory for coding agents and MCP clients.

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 MCPB.Free to use.
MCP server: One MCP server.
Evidence GateRun by its publisher: served from their own domain, namespace checked by the registry.
@dailyaiagents · External

Local checks for artifacts, declared claim evidence, and citation containment.

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

Hire, pay gaslessly, deliver and get paid between AI agents on BotHire (USDT/USDC, escrow).

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

Issue tracker and durable project memory for your coding agent, scoped to the folder you open.

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

Self-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path.

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

myspAIce, give your AI a social life: games, music, friendships. An immersive world. Just walk in.

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

Memory for AI agents that tracks beliefs over time and surfaces contradictions

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.
Cap Shield
@robinlidberg-dot · External

Context selection and compression for AI agents - recall measured, not claimed.

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 PyPI.Free to use.
MCP server: One MCP server.
Loreweave
@lets-order-some-fries · External

Durable agent memory over a markdown vault: bitemporal facts, timelines, hybrid graph search.

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

MCP server for AxionQuant financial data, including market, economic, SEC filing, and company data.

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

MCP server giving AI agents persistent SQLite memory that proves which lessons hold.

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.
pgops
@arzharch · External

Safe, audited PostgreSQL operations for AI agents: queries, migrations, EXPLAIN, containers

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 PyPI.Free to use.
MCP server: One MCP server.
Nutanix Prism Central
@wyre-ai · External

Multitenant Streamable HTTP bridge over Nutanix's official v4 API MCP server (Prism Central).

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

Validate EU VAT numbers (VIES), IBANs and EORI, look up company data (GLEIF) and VAT rates

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 PyPI.Free to use.
MCP server: One MCP server.
BanditDB
@banditdb · External

Persistent decision memory for agents — learns which action works in which context

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.
Synod Council
@naruminho · External

Durable symmetric deliberation between two AI agents, with isolated worktrees and peer review.

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.
kbdb
@diko316 · External

A searchable second brain for AI agents: ranked keyword and semantic search over your Markdown.

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 npm.Free to use.
MCP server: One MCP server.
SealRun by its publisher: served from their own domain, namespace checked by the registry.
@aurumflux20 · External

Stops agents double-charging across processes: exactly one execution, confirmed by the provider.

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.
Verdict
@dgotlieb · External

Sandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history

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 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