Odel

Software development

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

5,414 servers4,309 publishers15 tags

All of Software development

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
rrubocop
@adrianov · External

Fast RuboCop-compatible Ruby linter with MCP inspect and autocorrect tools.

2% 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 cargo.Free to use.
MCP server: One MCP server.
dbt-plan
@presentjay · External

Predicts the DDL a dbt change will execute, before you run it. Reads files, not the warehouse.

2% 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.
siGit CLI
@sigit · External

Run sigit.si locally: browse repos, search code, manage PRs, issues, and Cloud Sessions.

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 cargo.Free to use.
MCP server: One MCP server.
ArenaRun by its publisher: served from their own domain, namespace checked by the registry.
@dravensoft-dev · External

Arena by Dravensoft over MCP: the router, the references and every component document.

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.
KEPTA — the memory for AI systemsRun by its publisher: served from their own domain, namespace checked by the registry.
@damiantodorovic · External

Local encrypted memory for AI: hybrid search, 8 MCP tools, one file you own. Free, no cloud.

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.
DevTrack
@sraj0501 · External

Read local tickets, commits, pending actions, voice profile, and EOD context over MCP.

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 MCPB.Free to use.
MCP server: One MCP server.
Memwyre
@memwyreai · External

Universal persistent memory and knowledge retrieval layer for AI agents and LLMs.

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; it needs your API key.Free to use.
MCP server: One MCP server.
ResiliReplayRun by its publisher: served from their own domain, namespace checked by the registry.
@aliengineering-byte · External

Run bounded, deterministic MCP reliability tests and generate executable regressions.

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.
Verdict QARun by its publisher: served from their own domain, namespace checked by the registry.
@artjack · External

Read-only MCP server over Verdict QA state: verdicts, findings, flaky quarantine, history.

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.
LLM Preflight
@feronovak · External

Local, cross-provider preflight checks for LLM integration changes.

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 PyPI.Free to use.
MCP server: One MCP server.
Local GPU Imagegen
@chevalgrand520 · External

MCP-first control plane for ComfyUI workflows with explicit approvals and no silent downloads.

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.
ViewDoctor
@kamnevvladimir · External

Local SwiftUI changed/staged checks with compact agent output and multi-module ownership.

2% 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.
Dsh VerifyRun by its publisher: served from their own domain, namespace checked by the registry.
@263311487-ux · External

Agent-built web app quality gate. Real browser is the judge. PASS/FAIL with receipts.

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.
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.

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

Serves your design system and coding standards to coding agents, so they stop guessing.

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.
CodecanvasRun by its publisher: served from their own domain, namespace checked by the registry.
@donggyun112 · External

Python code intelligence for coding agents: call paths, control flow, and change impact.

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.
Agent CRM
@khaoss85 · External

Read-only docs for the Accordo CRM framework: what it proves, and where it stops.

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.
dompruner-mcp
@dong7812 · External

Strips layout noise via DOM AST; with a query, BM25 filters to relevant sections. No model or API.

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.
MCP Code Review Server
@goodjobwilliam · External

Code review as an MCP server — structured reviews with OWASP security scanning.

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.
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.
Evolith Architecture GovernanceRun by its publisher: served from their own domain, namespace checked by the registry.
@beyondnetcode · External

Executable architecture governance: an unevaluated rule is reported as a failure, never a pass.

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.
RTBlint
@aleksuix · External

Validate OpenRTB bid requests and responses against IAB specs. ARTF, Rust core.

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.
CodeSampleX
@r2cuerdame · External

Compatibility evidence from real builds: does this library API work on your versions and runtime?

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 MCPB.Free to use.
MCP server: One MCP server.
ChimeraForgeRun by its publisher: served from their own domain, namespace checked by the registry.
@sahil170595 · External

Local-first LLM deployment planner: GPU/VRAM sizing, cost and latency, with provenance

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 & privacyAI & agentsCloud & IT operationsData & webWork & productivityCommunicationDocuments & writingDesign & mediaNews & informationScience & researchHealth & fitnessEducation & careersTravel & placesHome & propertyEntertainment & hobbiesIndustry & transport