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.
Forge Engine
@forgeengine · External

Design spec + milestones AI coding agents read before building; drift flagged, changes reviewed.

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; no sign-in.Free to use.
MCP server: One MCP server.
Keel
@tdalbanmoreynas · External

Catches your AI coding agent when it games the tests - locked-test hashes, tamper detection.

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.Runs on your machine, installed from a package registry.Free to use.
MCP server: One MCP server.
Aifordatabase
@dann26parr69 · External

Query any database in plain English or SQL through a guardrailed, read-only data layer.

10% 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.The repository cannot be reached since 10 Oct.Free to use.
MCP server: One MCP server.
Myopic
@surajkgoyal · External

Code-review MCP: review a GitLab MR or GitHub PR against the whole codebase, not just the diff.

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.
sql-stewardRun by its publisher: served from their own domain, namespace checked by the registry.
@pawansingh3889 · External

The agent never writes SQL: queries compile from a semantic layer you control, PII refused first.

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.The repository is archived.Free to use.
MCP server: One MCP server.
TwiceshyRun by its publisher: served from their own domain, namespace checked by the registry.
@twiceshy · External

Experience memory for coding agents: validated traps, fixes and dead-ends at decision time.

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; it needs your API key.Free to use.
MCP server: One MCP server.
Garchi CMS MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@garchi · External

Manage structured website content in Garchi CMS through 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; you sign in with your account.Free to use.
MCP server: One MCP server.
Rami Code ReviewRun by its publisher: served from their own domain, namespace checked by the registry.
@rami · External

AI code review for GitHub PRs with an MCP autofix loop for Claude Code and Cursor

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

Versioned documentation registry and semantic search for AI tools and coding assistants.

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.
ZERNO LiteRun by its publisher: served from their own domain, namespace checked by the registry.
@zerno · External

Give AI agents secure access to ZERNO project briefs, tasks, and context over remote MCP.

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

Search Japanese company database

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; no sign-in.Free to use.
MCP server: One MCP server.
Mtok MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@mtok · External

Spot market for AI inference tokens. Buyers pay per draw in USDC on Base; sellers host delivery.

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.
Trunk Flaky TestsRun by its publisher: served from their own domain, namespace checked by the registry.
@trunk · External

Flaky test detection, root cause analysis, and fix suggestions for development teams.

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; you sign in with your account.Free to use.
MCP server: One MCP server.
MCP Hook Conformance
@studiomeyer · External

Audits MCP servers for Claude Code mcp_tool hook readiness: idempotency, latency, side-effects.

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.
MCP Protocol Conformance
@studiomeyer · External

MCP conformance test harness. JSON-RPC, OAuth 2.1 PKCE, schemas, smoke, annotations. CLI + lib.

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.
Scorecard MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@scorecard · External

MCP server providing access to the Scorecard API to evaluate and optimize LLM 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.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
Siteglass MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@siteglass · External

Archive any URL to a shareable rrweb/pdf/png snapshot + agent-driven web QA (scan, run E2E flows).

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.
OneSource MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@onesource · External

Blockchain data, Deepstate and Standard Reserve markets, live chain queries, and API docs

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Waitloop
@zexiro · External

Agent-first waitlists: hosted signup pages with referral ranking. One tool call returns a live page.

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; it needs your API key.Free to use.
MCP server: One MCP server.
GitInProgress
@ysk-abe · External

Group your AI's changes into focused commit candidates; nothing lands until you approve.

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 a package registry.Free to use.
MCP server: One MCP server.
Bookie
@yuens1002 · External

Double-entry bookkeeping MCP server — import bank CSVs, categorize, reconcile, tax reports.

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.
Random Design
@yanislav-igonin · External

Generate randomized English Markdown frontend design directions from curated catalogs.

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.
Git Summary
@yifanyifan897645 · External

Git repo intelligence: summaries, blame, changelogs, branch health, and history search

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.
Mini App
@ynishi · External

Agent-First CRUD store MCP server — 1 daemon per table, schema.yaml driven, SQLite backend

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.

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