Odel

AI & agents

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

13,113 servers7,073 publishers11 tags

All of AI & agents

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

Cross-tool decision memory for AI coding agents: search your decision graph, check changes over MCP.

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.
Keel
@lutfizp · External

Control plane MCP that dedups scanner output, rate-limits hosts, and runs non-destructive proofs.

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.
Kubernetes
@dockndevai · External

Kubernetes monitoring & ops for AI agents — safe-by-default access modes and guards.

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.
Affine.Earth Math CourtRun by its publisher: served from their own domain, namespace checked by the registry.
@affine · External

No-float UUM-8D Math Court. Integer courts and certified MCP. Floats refused.

18% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
chat-recallRun by its publisher: served from their own domain, namespace checked by the registry.
@munhq · External

One searchable history across every AI coding tool, with secret scanning and a shared task board.

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; you sign in with your account.Free to use.
MCP server: One MCP server.
LatticeNetRun by its publisher: served from their own domain, namespace checked by the registry.
@latticenet · External

Publish articles and notes under your own byline, to a readership of other AI agents.

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; you sign in with your account.Free to use.
MCP server: One MCP server.
IntoDNS.ai DNS & Email Security ScannerRun by its publisher: served from their own domain, namespace checked by the registry.
@intodns · External

DNS and email security: check SPF, DKIM, DMARC, DNSSEC, DANE and build the records. 45 tools.

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.
MapSmithRun by its publisher: served from their own domain, namespace checked by the registry.
@mapsmith-ai · External

Deterministic GIS geoprocessing with verifiable provenance on every output

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.
Securedact MCP
@giganteshji · External

Local-first privacy MCP server for sensitive AI workflows

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.
ApocData MCP
@apocdata · External

天启至数 ApocData - MCP Server for A-share market data (46 free, no-auth endpoints)

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.
WhatsApp Connect
@idle-sync · External

Read, search, and send personal WhatsApp messages from any MCP client, behind a send-confirm gate.

14% 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 MCPB.Free to use.
MCP server: One MCP server.
Todox
@beydemirfurkan · External

Memory for coding agents: the decisions, the dead ends, and where the last session stopped.

6% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.A remote server; it needs your API key.Free to use.
MCP server: One MCP server.
Cybercentry VerificationRun by its publisher: served from their own domain, namespace checked by the registry.
@cybercentry · External

Twelve tools: token, wallet, contract and site security. Two free, the rest $1 in USDC over x402.

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

An MCP memory server. One memory your agents share — across models, devices and apps.

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; you sign in with your account.Free to use.
MCP server: One MCP server.
Inkwell
@veronchenko · External

Persistent memory for AI agents: Markdown entries, hybrid search, typed graph links

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 Docker.Free to use.
MCP server: One MCP server.
HYPD AI - Paid Ads & Analytics
@hypd-ai · External

Google Ads, Meta (Facebook) Ads, GA4 and Merchant Center analysis in plain language. Read-only.

10% 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.
Dibs
@agenxy · External

Tells an AI agent when another is already doing its work. Board, typed mail, directory claims.

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 MCPB.Free to use.
MCP server: One MCP server.
SanctionsAI
@kindrat86 · External

OFAC sanctions screening for AI agents: 1,050 wallets, 19,389 SDN names, <100ms. Free tier, no key.

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.Free to use.
MCP server: One MCP server.
Model Council
@totti0135 · External

Consult other LLMs as tools — ask them, compare their answers, synthesize a conclusion.

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

Governance validation for Semantic Data Charter instances; returns OASIS XACML decisions.

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.
Stateark
@askrion · External

Local-first version control for AI work. Savepoint and resume your project state across chats.

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.
mcp-audit
@firatmio · External

Transparent audit proxy for MCP servers: logs every tool call, flags poisoning and rug pulls.

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.
HexWitness
@siaginw · External

Durable, build-scoped reverse-engineering evidence memory and query tools for AI agents.

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.
Meet Live Assist
@krystiangw · External

Your own agent inside a live Google Meet or Zoom call. Local-first, no hosted service.

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.

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