Context+

Context+ is a semantic intelligence server that transforms codebases into searchable, hierarchical feature graphs using RAG, Tree-sitter AST, and spectral clustering. It provides tools for deep code discovery, blast radius analysis, and memory graph management for high-accuracy engineering tasks.

→ ForLoopCodes/contextplus · listed on glama

Install from

Glama

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings

🚨

Known vulnerabilities in dependencies: 1 critical, 3 high

Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.

🔐

You'll be asked for 2 credentials: CONTEXTPLUS_OPENAI_API_KEY, OPENAI_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// required environment variables

This server reads these from process.env. You'll be asked to provide them before it can run.

configCONTEXTPLUS_EMBED_BATCH_SIZE— string (parsed as number) 8 Embedding batch size per GPU call, clamped to 5-10

configCONTEXTPLUS_EMBED_CHUNK_CHARS— string (parsed as number) 2000 Per-chunk chars before merge, clamped to 256-8000

configCONTEXTPLUS_EMBED_LOW_VRAM— string (parsed as boolean) - Optional Ollama embed runtime low_vram override

configCONTEXTPLUS_EMBED_MAIN_GPU— string (parsed as number) - Optional Ollama embed runtime main_gpu override

configCONTEXTPLUS_EMBED_NUM_BATCH— string (parsed as number) - Optional Ollama embed runtime num_batch override

configCONTEXTPLUS_EMBED_NUM_CTX— string (parsed as number) - Optional Ollama embed runtime num_ctx override

configCONTEXTPLUS_EMBED_NUM_GPU— string (parsed as number) - Optional Ollama embed runtime num_gpu override

configCONTEXTPLUS_EMBED_NUM_THREAD— string (parsed as number) - Optional Ollama embed runtime num_thread override

configCONTEXTPLUS_EMBED_PROVIDER— Context+ supports two embedding backends controlled by :

configCONTEXTPLUS_EMBED_TRACKER— string (parsed as boolean) true Enable realtime embedding refresh on file changes

configCONTEXTPLUS_EMBED_TRACKER_DEBOUNCE_MS— string (parsed as number) 700 Debounce window before tracker refresh

configCONTEXTPLUS_EMBED_TRACKER_MAX_FILES— string (parsed as number) 8 Max changed files processed per tracker tick, clamped to 5-10

configCONTEXTPLUS_IDLE_TIMEOUT_MS

configCONTEXTPLUS_MAX_EMBED_FILE_SIZE— string (parsed as number) 51200 Skip non-code text files larger than this many bytes

🔐 secretCONTEXTPLUS_OPENAI_API_KEY— "": "YOUR_GEMINI_API_KEY",

configCONTEXTPLUS_OPENAI_BASE_URL— "": "https://generativelanguage.googleapis.com/v1beta/openai",

configCONTEXTPLUS_OPENAI_CHAT_MODEL— Note: The semantic_navigate tool also uses a chat model for cluster labeling. When using the openai provider, set (default: gpt-4o-mini).

configCONTEXTPLUS_OPENAI_EMBED_MODEL— "": "text-embedding-004"

configCONTEXTPLUS_PARENT_POLL_MS

configOLLAMA_CHAT_MODEL— "": "gemma2:27b",

configOLLAMA_EMBED_MODEL— "": "nomic-embed-text",

configOLLAMA_HOST

🔐 secretOPENAI_API_KEY— "": "sk-...",

configOPENAI_BASE_URL— CONTEXTPLUS_OPENAI_BASE_URL string https://api.openai.com/v1 OpenAI-compatible endpoint URL (alias: )

configOPENAI_CHAT_MODEL— CONTEXTPLUS_OPENAI_CHAT_MODEL string gpt-4o-mini OpenAI-compatible chat model for labeling (alias: )

configOPENAI_EMBED_MODEL— "": "text-embedding-3-small"

// full audit trail

The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.

// improvement guidance — verified publishers only

We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Score](https://m8ven.ai/badge/mcp/forloopcodes-contextplus-48l7v9)](https://m8ven.ai/mcp/forloopcodes-contextplus-48l7v9)

commit: 36456cb054c40c775f82389c6260f8ee5379861f

code hash: 690855f27f1b141aa3f051646b49708d67a7bb1753438329bc4c7b6f119183a0

verified: 4/11/2026, 2:44:00 PM

view raw JSON →