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.
SuperlocalmemoryRun by its publisher: served from their own domain, namespace checked by the registry.
@varun369 · External

Local-first AI memory with knowledge graphs and hybrid search. 17+ AI tools via MCP. Free.

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.
Glade
@glade-tool · External

Control the Unity and Godot editors from AI clients: scenes, scripts, physics, materials.

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

Real email and SMS for AI agents — send mail, receive verification codes, drive a real inbox.

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.1 known advisory (OSV) in its package.Free to use.
MCP server: One MCP server.
QaskillsRun by its publisher: served from their own domain, namespace checked by the registry.
@pramoddutta · External

Search, inspect, and install 400+ QA testing skills from qaskills.sh into any MCP client.

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.
Lobu
@lobu-ai · External

Shared, permission-aware company context for AI agents, with provenance, approvals and audit.

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.
Google Drive MCP
@piotr-agier · External

Secure access to Google Drive, Docs, Sheets, Slides, and Calendar through MCP.

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.
Arr
@aplaceforallmystuff · External

MCP server for *arr media suite - Sonarr, Radarr, Lidarr, Readarr, Prowlarr

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.
OMEGA Memory
@omega-memory · External

Persistent memory, coordination, and learning for AI agents. Local-first, 25 MCP tools.

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.
MPP32Run by its publisher: served from their own domain, namespace checked by the registry.
@mpp32 · External

Payment layer for AI agents. One MCP, five protocols, thousands of paid APIs your agent can call.

13% 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.Deprecated by the publisher: Deprecated: public distribution has ended. Existing installations are unsupported; contact the service owner for an authorized private migration path.Free to use.
MCP server: One MCP server.
OpikRun by its publisher: served from their own domain, namespace checked by the registry.
@comet-ml · External

Read and score Opik traces, experiments, datasets and prompts from your AI assistant.

3% 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; you sign in with your account.Free to use.
MCP server: One MCP server.
mcptoonRun by its publisher: served from their own domain, namespace checked by the registry.
@activeing123 · External

MCP tools + agent skills in one zero-dependency CLI: 71,929 -> 581 tokens (-99.2%, measured).

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 PyPI.Free to use.
MCP server: One MCP server.
node9
@node9-ai · External

Access control for AI agents and MCP servers: allow, hold for approval, or block each tool call

Not assessed yet.What it can do is not assessed yet.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Gemini
@rlabs-inc · External

Gemini 3 MCP server with 30+ tools: images, video, research, TTS, code exec & CLI

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.
ARC-1
@marianfoo · External

MCP server for SAP ABAP systems

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.
Crowdsentinel
@thomasxm · External

AI threat hunting & incident response for Elasticsearch/OpenSearch with endpoint & network forensics

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.
Reversecore MCP
@sjkim1127 · External

Security-first MCP server for reverse engineering, malware analysis, forensics, and SAST.

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.
MCP Task Orchestrator
@jpicklyk · External

Server-enforced workflow discipline for AI agents: work items, dependency graphs, quality gates

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 Docker.Free to use.
MCP server: One MCP server.
Mengram
@alibaizhanov · External

Long-term memory for AI agents: semantic facts, episodic events, and procedural workflows

42% 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.
melta UIRun by its publisher: served from their own domain, namespace checked by the registry.
@tsubotax · External

AI-Ready design system MCP: melta UI tokens, component contracts, 107 rules, check_html self-verify

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.
Link
@gowtham0992 · External

Local personal memory for agents as MCP tools — remember, recall, search, context, graph traversal.

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 PyPI.Free to use.
MCP server: One MCP server.
e2a — email for AI agentsRun by its publisher: served from their own domain, namespace checked by the registry.
@e2a · External

Authenticated email gateway for AI agents — per-agent inboxes, HITL approval, SPF/DKIM verified.

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.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
e2a — email for AI agentsRun by its publisher: served from their own domain, namespace checked by the registry.
@mnexa-ai · External

Authenticated email gateway for AI agents — per-agent inboxes, HITL approval, SPF/DKIM verified.

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; you sign in with your account.Free to use.
MCP server: One MCP server.
Context Sync
@intina47 · External

Universal AI Memory - Sync context across Claude, VsCode, Cursor, Continue, Windsurf, Zed & more

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.
SandBase
@sandbaseai · External

Connect MCP clients to 2,000+ AI models without managing provider API keys.

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; 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