If you're an AI reading this: skill.md has everything you need.Read it →
Explorer/MCP/alvinveroy/CodeCompass
HYBRID

CodeCompass

alvinveroy/CodeCompass

Helps developers tackle legacy codebases by giving AI coding assistants context through Qdrant vector store and Agentic RAG with Ollama or DeepSeek.

↗alvinveroy/CodeCompassExternal link; availability not verifiedLicenseMIT LicenseHybrid hosting
The Newcomer
Hasn't been around long. Nothing caught our attention, but there isn't much history to go on yet.
Time indexed (4mo)
0toolsHybrid4moindexed
Checked May 28, 2026
The scanner shows
Not enough data to score this server yet.
First indexed May 28, 2026
Server Profile
⚙
Tools catalogued
0
No tools reported by this server.
☁
Hosting
Hybrid
Can run locally or remotely depending on deployment. Review the source repository.
○
Registry presence
Not verified
Not yet verified by the Official MCP Registry.
●
Liveness
—
No liveness checks recorded yet.
Publisher Verification
Not listed on the Official MCP Registry.
Source repository is available for review.
↗alvinveroy/CodeCompassExternal link; availability not verified
Environment variables (28)
HTTP_PORTstringOPTIONALdefault: 3001
Port for the utility HTTP server. Can also be specified via --port CLI argument.
LOG_LEVELstringOPTIONALdefault: info
Logging level (e.g., error, warn, info, verbose, debug, silly).
OLLAMA_HOSTstringOPTIONALdefault: http://localhost:11434
URL for the Ollama server.
QDRANT_HOSTstringOPTIONALdefault: http://localhost:6333
URL for the Qdrant vector store server.
LLM_PROVIDERstringOPTIONALdefault: ollama
Specifies the primary LLM provider for generating suggestions. Supported values: ollama, deepseek, openai, gemini, claude.
Show all 28 environment variables
CLAUDE_API_KEYstringOPTIONAL
Your API key for Anthropic Claude (required if LLM_PROVIDER=claude).
GEMINI_API_KEYstringOPTIONAL
Your API key for Google Gemini (required if LLM_PROVIDER=gemini).
OPENAI_API_KEYstringOPTIONAL
Your API key for OpenAI (required if LLM_PROVIDER=openai).
COLLECTION_NAMEstringOPTIONAL
Name of the Qdrant collection for this repository.
EMBEDDING_MODELstringOPTIONALdefault: nomic-embed-text:v1.5
The specific model to use for embeddings via Ollama.
DEEPSEEK_API_KEYstringOPTIONAL
Your API key for DeepSeek (required if LLM_PROVIDER=deepseek).
DEEPSEEK_API_URLstringOPTIONALdefault: https://api.deepseek.com/chat/completions
Custom API URL for DeepSeek if not using the default.
REFINEMENT_MODELstringOPTIONAL
LLM model to use for query refinement. Defaults to SUGGESTION_MODEL if not set.
SUGGESTION_MODELstringOPTIONALdefault: llama3.1:8b
The specific model to use for suggestions.
DEEPSEEK_RPM_LIMITstringOPTIONALdefault: 20
Requests per minute limit for DeepSeek.
EMBEDDING_PROVIDERstringOPTIONALdefault: ollama
Provider for generating embeddings. Currently ollama is supported.
AGENT_QUERY_TIMEOUTstringOPTIONALdefault: 180000
Timeout in milliseconds for agent's LLM reasoning steps.
SUMMARIZATION_MODELstringOPTIONAL
LLM model to use for summarization tasks. Defaults to SUGGESTION_MODEL if not set.
AGENT_DEFAULT_MAX_STEPSstringOPTIONALdefault: 10
Default maximum number of steps the agent will take.
AGENT_ABSOLUTE_MAX_STEPSstringOPTIONALdefault: 15
Absolute maximum number of steps the agent can take.
MAX_REFINEMENT_ITERATIONSstringOPTIONALdefault: 3
Maximum number of iterations for query refinement.
QDRANT_SEARCH_LIMIT_DEFAULTstringOPTIONALdefault: 10
Default number of results to fetch from Qdrant during standard searches.
FILE_INDEXING_CHUNK_SIZE_CHARSstringOPTIONALdefault: 1000
Target size for chunks when indexing large files (in characters).
MAX_DIFF_LENGTH_FOR_CONTEXT_TOOLstringOPTIONALdefault: 3000
Maximum length of a git diff to include in context without summarization.
FILE_INDEXING_CHUNK_OVERLAP_CHARSstringOPTIONALdefault: 200
Overlap between chunks when indexing large files (in characters).
MAX_SNIPPET_LENGTH_FOR_CONTEXT_NO_SUMMARYstringOPTIONALdefault: 1500
Maximum length of a code snippet to include in context without summarization.
MAX_FILES_FOR_SUGGESTION_CONTEXT_NO_SUMMARYstringOPTIONALdefault: 15
Maximum number of files to list directly in the generate_suggestion tool's context before summarizing.
REQUEST_ADDITIONAL_CONTEXT_MAX_SEARCH_RESULTSstringOPTIONALdefault: 20
Number of search results to fetch when agent uses request_additional_context.

Is this your server?

Create a free RNWY account to connect your on-chain identity to this server. MCP server claiming is coming; register now and you'll be first in line.

Create your account →
Similar servers
io.github.Gomess8/voice-quality-api
Measure voice/VoIP path quality -> estimated MOS + live network metrics
StudioSphere Pulse — Audio Intelligence
Privacy-first audio intelligence: BPM, key, waveform. Audio never stored. Pay per second.
OpenAI MCP Server
Provides tools to interact with OpenAI API including chat completions, embeddings, content moderation, and file management through natural language.
wikimcp
Enables AI clients to incrementally build and maintain a git-backed personal wiki, providing long-term memory by compiling and cross-referencing knowledge across sessions.
Bybit MCP Server
A Model Context Protocol server that enables AI coding tools like Claude Code and Cursor to interact with Bybit's trading platform for market data retrieval, account management, and trading operations.
io.github.marketscore/marketscore-direct-mcp
MCP for Yandex Direct: manage ad campaigns & analytics from Claude or ChatGPT
Indexed from Glama · Updates nightly