Odel

Software development

Code, repositories, reviews, tests, debugging, databases and developer docs.

5,433 servers4,326 publishers15 tags

All of Software development

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

Decentralized AI inference (weather, deepfake detection, LLMs) with x402 USDC micropayments.

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

Ask your AI agent why your tests are failing. Instant analysis on failures and regressions.

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.
Slipstream
@tathagat22 · External

Shared distillation cache for AI agents — every fetch ~73-89% fewer tokens via a shared cache.

5% 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.
Matih Labs MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@matih · External

The grounded data layer for any LLM: governed SQL, metrics, lineage and catalog over your data.

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

Run 100+ AI models — image, video, audio, 3D — through one API with pay-per-use billing.

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.
TAPD MCP Server
@sun-jingtao · External

在 Cursor/Copilot 中查询、分析和回填 TAPD bug / 需求

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.
Hive Consult
@srotzin · External

Agent-to-agent reasoning-as-a-service: chain-of-thought, analysis, and decision support.

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

Debug and develop MCP servers with hot-swapping, session recording, and playback testing

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.
Hive Compute
@srotzin · External

HiveCompute MCP Server — decentralized inference router for AI agents

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; no sign-in.Free to use.
MCP server: One MCP server.
MADB — Agent Memory Database
@spshkar84 · External

Durable causal memory for AI agents — semantic recall, causal lineage, and skills. Local-first.

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.Package madb-mcp-server was yanked by its publisher.Free to use.
MCP server: One MCP server.
YeetIt
@snappyio · External

Instant web publishing for AI agents. POST HTML, get a live URL. No account needed.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Dear Claude
@sns45 · External

Spawn Claude Code instances from 6 platforms when 'Dear Claude' is mentioned.

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.
lo-eyesRun by its publisher: served from their own domain, namespace checked by the registry.
@sophiacave · External

Visual accessibility inspector. WCAG contrast, touch targets, heading audits, screenshots.

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.
SmartpolicyRun by its publisher: served from their own domain, namespace checked by the registry.
@smartpolicy-protocol · External

Runtime authorization for AI agents and smart contracts via an immutable on-chain policy registry

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.
AI Optimizer
@shivam-app-developers · External

MCP server that cuts AI coding agent token usage via framework-aware context optimization

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.
GitHub Project Info
@shubhtoy · External

Read public GitHub Projects v2 boards without auth — items, fields, story points, priority.

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

Capture, replay, and debug failures with portable, executable bug artifacts

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 npm.Free to use.
MCP server: One MCP server.
CyberLens
@shadoprizm · External

Security scanning for websites, public repositories, and Open CLAW skills.

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Cds Db Nlquery
@shahidla · External

MCP server for natural-language queries against SAP CAP db-layer entities via real CQN/SQL JOINs.

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.
Berth
@seayniclabs · External

Database management — query, schema inspection, migrations for PostgreSQL, MySQL, SQLite.

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.
Mooring
@seayniclabs · External

Git and GitHub operations — repo status, diffs, branches, PRs, issues, and Actions.

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

Interact with the Beans CLI issue tracker agentically

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.
Schemaguard
@sethclawd-prog · External

API Schema Drift Monitor — detect breaking changes in OpenAPI specs

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.
sncro
@scottconfusedgorilla · External

Live browser debugging for AI assistants — DOM, console, network via MCP.

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; no sign-in.Free to use.

More topics

Sales & customersMarketing & advertisingShopping & e-commerceBusiness financePersonal finance & investingLegal & governmentSecurity & privacyAI & agentsCloud & IT operationsData & webWork & productivityCommunicationDocuments & writingDesign & mediaNews & informationScience & researchHealth & fitnessEducation & careersTravel & placesHome & propertyEntertainment & hobbiesIndustry & transport