Massive Context MCP server
Handles 10M+ token contexts with chunking, sub-queries, and local Ollama inference.
1 stars
Reviews
Write oneNobody has reviewed Massive Context yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Massive Context tools (17, 1 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
rlm_auto_analyzeAutomatically detect content type and analyze with optimal chunking strategy.
rlm_chunk_contextChunk a loaded context by strategy. Returns chunk metadata, not full content.
rlm_execwrite actionExecute Python code against a loaded context in a sandboxed subprocess.
rlm_filter_contextFilter context using regex/string operations. Creates a new filtered context.
rlm_firewall_statusCheck the status of the code execution firewall.
rlm_get_chunkGet a specific chunk by index. Use after chunking to retrieve individual pieces.
rlm_get_resultsRetrieve stored results for aggregation.
rlm_inspect_contextInspect a loaded context - get structure info without loading full content into prompt.
rlm_list_contextsList all loaded contexts and their metadata.
rlm_load_contextLoad a large context as an external variable.
rlm_ollama_statusCheck Ollama server status and available models.
rlm_setup_ollamaInstall Ollama via Homebrew (macOS).
rlm_setup_ollama_directInstall Ollama via direct download (macOS).
rlm_store_resultStore a sub-call result for later aggregation.
rlm_sub_queryMake a sub-LLM call on a chunk or filtered context. Core of recursive pattern.
rlm_sub_query_batchProcess multiple chunks in parallel. Respects concurrency limit to manage system resources.
rlm_system_checkCheck if system meets requirements for Ollama with gemma3:12b.
Public scan report
scanner v0.1.10 · 2026-10-01 · same rubric, same numbers if you re-run it
- Code scan7 source files scanned15/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 249 days ago4/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Findings (2)
- mediumsubprocess with shell=True
exec.shell-truemassive_context_mcp-3.0.1/src/rlm_mcp_server.py: … "Process spawning"), ("shell=True", "Shell execution enabled"), … - mediumeval / new Function used
exec.evalmassive_context_mcp-3.0.1/src/rlm_mcp_server.py: …bprocess execution"), ("eval(", "Dynamic code evaluation"), …
Install Massive Context in Claude Code, Cursor or VS Code
claude mcp add massive-context-mcp -- uvx massive-context-mcp
Massive Context: common questions
- Is Massive Context MCP server safe?
- With care: it is graded C, so read the findings first (60/100). Read the Massive Context safety report
- How do I install Massive Context?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Massive Context need an API key?
- No secret keys are declared. It reads 4 settings from the environment.
- Is Massive Context maintained?
- The last commit was 261 days ago (2026-01-25). The latest release is v3.0.1.
- What can I use instead of Massive Context?
- Servers from other publishers that do the same job: Codebase Memory MCP server.
Alternatives to Massive Context
Same job from other publishers: the closest match first, then the best rated.
- Codebase MemoryCodebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.not reviewedWidely usedC