Massive Context Mcp
Handles contexts too large for a single prompt by breaking them into chunks, running sub-queries via local Ollama models (gemma3:12b by default), and aggregating results. Exposes tools like rlm_auto_analyze for one-shot analysis with automatic content-type detection, rlm_exec for running sandboxed Python code against loaded contexts, and rlm_sub_query_batch for parallel chunk processing. Includes Ollama setup tools that can install via Homebrew or direct download for locked-down systems. The recursive pattern keeps raw context out of the main prompt while letting you inspect structure, filter with regex, and synthesize findings. Useful when you need to analyze logs, codebases, or documents in the 10M+ token range without hitting context limits or paying cloud inference costs.
- tools
- 16
- transport
- STDIO
- env vars
- 2
- last updated
- Jan 19, 2026
Tools
16 toolsPublic tool metadata for what this MCP can expose to an agent.
rlm_system_checkCheck system requirements — verify macOS, Apple Silicon, 16GB+ RAM, Homebrew
Check system requirements — verify macOS, Apple Silicon, 16GB+ RAM, Homebrew
No parameter schema in public metadata yet.
rlm_setup_ollamaInstall via Homebrew — managed service, auto-updates, requires Homebrew
Install via Homebrew — managed service, auto-updates, requires Homebrew
No parameter schema in public metadata yet.
rlm_setup_ollama_directInstall via direct download — no sudo, fully headless, works on locked-down machines
Install via direct download — no sudo, fully headless, works on locked-down machines
No parameter schema in public metadata yet.
rlm_ollama_statusCheck Ollama availability — detect if free local inference is available
Check Ollama availability — detect if free local inference is available
No parameter schema in public metadata yet.
rlm_auto_analyzeOne-step analysis — auto-detects type, chunks, and queries
One-step analysis — auto-detects type, chunks, and queries
No parameter schema in public metadata yet.
rlm_load_contextLoad context as external variable
Load context as external variable
No parameter schema in public metadata yet.
rlm_inspect_contextGet structure info without loading into prompt
Get structure info without loading into prompt
No parameter schema in public metadata yet.
rlm_chunk_contextChunk by lines/chars/paragraphs
Chunk by lines/chars/paragraphs
No parameter schema in public metadata yet.
rlm_get_chunkRetrieve specific chunk
Retrieve specific chunk
No parameter schema in public metadata yet.
rlm_filter_contextFilter with regex (keep/remove matching lines)
Filter with regex (keep/remove matching lines)
No parameter schema in public metadata yet.
rlm_execExecute Python code against loaded context (sandboxed)
Execute Python code against loaded context (sandboxed)
No parameter schema in public metadata yet.
rlm_sub_queryMake sub-LLM call on chunk
Make sub-LLM call on chunk
No parameter schema in public metadata yet.
rlm_sub_query_batchProcess multiple chunks in parallel
Process multiple chunks in parallel
No parameter schema in public metadata yet.
rlm_store_resultStore sub-call result for aggregation
Store sub-call result for aggregation
No parameter schema in public metadata yet.
rlm_get_resultsRetrieve stored results
Retrieve stored results
No parameter schema in public metadata yet.
rlm_list_contextsList all loaded contexts
List all loaded contexts
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
RLM_DATA_DIRDirectory for storing context data
OLLAMA_URLURL for Ollama server (default: http://localhost:11434)
Readme
Details
- Repository
- github.com/egoughnour/massive-context-mcp
- Category
- AI & LLM Tools
- Package
massive-context-mcp- Transport
- STDIO
- Registry
- MCP registry, active
More from egoughnour
Related AI & LLM Tools MCP servers
View all
Secrets Audit Mcpeltociear/secrets-audit-mcpDetects leaked secrets & API keys: 32+ provider rules (AWS, GitHub, Stripe, OpenAI…), zero deps.0stars
Closeread Verifyfreeguy-ai/closeread-verifyA verified dependency-audit verdict any AI agent can call over MCP, not a raw scan.0stars
ESG MCP Serversfreminder/esg-mcp-servers31 MCP tools for ESG data extraction, PDF processing, vector search, and EU regulation analysis.0stars
Cyphrexgetcyphrex/platformChecks AI agent actions before they run. Signed, RFC 3161 timestamped evidence for audits.0stars
TrustLayergoatgaucho/trust-layerAgent reputation scoring: trust scores, Sybil detection, cross-chain identity for 133K+ agents0stars
Intelligence Mcpgoodmeta/intelligence-mcpAgent payments ecosystem intelligence. Scans GitHub/HN/npm across AP2, ACP, x402, MPP, UCP.0stars