Context First Mcp
A 37-tool suite built around `context_loop`, an orchestrator that runs eight checks per turn: recap, conflict detection, ambiguity scanning, entropy monitoring, abstention logic, tool discovery, drift detection, and synthesis. Returns a single directive with action type, context health score, extracted facts, and next-tool suggestions. Includes persistent memory with graph queries, five advanced reasoning engines (InftyThink, Coconut, ExtraCoT, MindEvolution, KAG-Thinker), and seven truthfulness verifiers including neighborhood consistency checks and self-correction. Also ships sandbox quarantine for isolating sub-task contexts and a structured research pipeline. Reach for this when long conversations start contradicting themselves or when you need the AI to ask clarifying questions instead of guessing. Works over stdio or as a Vercel-deployed HTTP endpoint.
- tools
- 36
- transport
- STDIO
- last updated
- Apr 14, 2026
Tools
36 toolsPublic tool metadata for what this MCP can expose to an agent.
context_loopOne-call orchestrator. Runs 8 stages (ingest→recap→conflict→ambiguity→entropy→abstention→discovery→synthesis) and returns a single directive with action, contextHealth score, extracted facts, and suggested next tools
One-call orchestrator. Runs 8 stages (ingest→recap→conflict→ambiguity→entropy→abstention→discovery→synthesis) and returns a single directive with action, contextHealth score, extracted facts, and suggested next tools
No parameter schema in public metadata yet.
recap_conversationExtracts hidden intent, key decisions, and produces consolidated state summaries
Extracts hidden intent, key decisions, and produces consolidated state summaries
No parameter schema in public metadata yet.
detect_conflictsCompares new input against ground truth; surfaces contradictions
Compares new input against ground truth; surfaces contradictions
No parameter schema in public metadata yet.
check_ambiguityIdentifies underspecified requirements and generates clarifying questions
Identifies underspecified requirements and generates clarifying questions
No parameter schema in public metadata yet.
verify_executionValidates whether tool outputs actually achieved the stated goal
Validates whether tool outputs actually achieved the stated goal
No parameter schema in public metadata yet.
entropy_monitorProxy-entropy scoring via lexical diversity, contradiction density, hedge frequency, and n-gram repetition (ERGO)
Proxy-entropy scoring via lexical diversity, contradiction density, hedge frequency, and n-gram repetition (ERGO)
No parameter schema in public metadata yet.
abstention_check5-dimension confidence scoring — abstains with questions rather than hallucinating (RLAAR)
5-dimension confidence scoring — abstains with questions rather than hallucinating (RLAAR)
No parameter schema in public metadata yet.
detect_driftDetects conversation drift from the original intent
Detects conversation drift from the original intent
No parameter schema in public metadata yet.
check_depthEvaluates response depth against question complexity
Evaluates response depth against question complexity
No parameter schema in public metadata yet.
get_stateRetrieve confirmed facts and task status
Retrieve confirmed facts and task status
No parameter schema in public metadata yet.
set_stateLock in ground truth — subsequent conflict checks run against these values
Lock in ground truth — subsequent conflict checks run against these values
No parameter schema in public metadata yet.
clear_stateReset specific keys or all state
Reset specific keys or all state
No parameter schema in public metadata yet.
get_history_summaryCompressed conversation history with intent annotations
Compressed conversation history with intent annotations
No parameter schema in public metadata yet.
discover_toolsNatural-language tool routing — returns only semantically relevant tools, reducing context bloat by up to 98%
Natural-language tool routing — returns only semantically relevant tools, reducing context bloat by up to 98%
No parameter schema in public metadata yet.
quarantine_contextCreate isolated memory silos for sub-tasks, preventing intent dilution
Create isolated memory silos for sub-tasks, preventing intent dilution
No parameter schema in public metadata yet.
merge_quarantineMerge silo results with noise filtering — only promoted keys return to main context
Merge silo results with noise filtering — only promoted keys return to main context
No parameter schema in public metadata yet.
memory_storeStore findings, decisions, and intermediate results with metadata
Store findings, decisions, and intermediate results with metadata
No parameter schema in public metadata yet.
memory_recallRetrieve relevant memories by semantic query
Retrieve relevant memories by semantic query
No parameter schema in public metadata yet.
memory_compactCompress and consolidate memory entries
Compress and consolidate memory entries
No parameter schema in public metadata yet.
memory_graphBuild and query a knowledge graph from stored memories
Build and query a knowledge graph from stored memories
No parameter schema in public metadata yet.
memory_inspectInspect memory store contents and statistics
Inspect memory store contents and statistics
No parameter schema in public metadata yet.
memory_curateDeduplicate and organize memory entries
Deduplicate and organize memory entries
No parameter schema in public metadata yet.
inftythink_reasonInfinite-depth reasoning with adaptive stopping
Infinite-depth reasoning with adaptive stopping
No parameter schema in public metadata yet.
coconut_reasonChain-of-Continuous-Thought in latent space
Chain-of-Continuous-Thought in latent space
No parameter schema in public metadata yet.
extracot_compressCompress chain-of-thought while preserving reasoning fidelity
Compress chain-of-thought while preserving reasoning fidelity
No parameter schema in public metadata yet.
mindevolution_solveEvolutionary search over the solution space
Evolutionary search over the solution space
No parameter schema in public metadata yet.
kagthinker_solveKnowledge-augmented generation with structured thinking
Knowledge-augmented generation with structured thinking
No parameter schema in public metadata yet.
probe_internal_stateProbe model consistency across paraphrased prompts
Probe model consistency across paraphrased prompts
No parameter schema in public metadata yet.
detect_truth_directionDetect whether model reasoning is trending toward or away from truth
Detect whether model reasoning is trending toward or away from truth
No parameter schema in public metadata yet.
ncb_checkNeighborhood consistency check across semantically equivalent inputs
Neighborhood consistency check across semantically equivalent inputs
No parameter schema in public metadata yet.
check_logical_consistencyVerify logical coherence of reasoning chains
Verify logical coherence of reasoning chains
No parameter schema in public metadata yet.
verify_firstPre-verification before committing to claims
Pre-verification before committing to claims
No parameter schema in public metadata yet.
ioe_self_correctIntrinsic-extrinsic self-correction
Intrinsic-extrinsic self-correction
No parameter schema in public metadata yet.
self_critiqueStructured self-critique with improvement suggestions
Structured self-critique with improvement suggestions
No parameter schema in public metadata yet.
research_pipelineStructured research orchestration across init → gather → analyze → verify → finalize, writing files autonomously to disk
Structured research orchestration across init → gather → analyze → verify → finalize, writing files autonomously to disk
No parameter schema in public metadata yet.
export_research_filesWrites every verified report chunk and/or every raw evidence batch to disk in a single call
Writes every verified report chunk and/or every raw evidence batch to disk in a single call
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 languageReadme
Context-First MCP
The MCP server that keeps your AI grounded, coherent, and honest — across every turn.
npx context-first-mcp
Works instantly with Claude Desktop · Cursor · VS Code · any MCP client · Vercel remote — zero API keys needed.
Details
- Repository
- github.com/xjtlumedia/context-first-mcp
- Categories
- Sales & Marketing, AI & LLM Tools, Automation & Workflows
- Package
context-first-mcp- Transport
- STDIO
- Registry
- MCP registry, active
More from xjtlumedia
Related Sales & Marketing MCP servers
View all
Vigilix: French company & address datazekinht0/vigilix-mcpFrench company, BODACC, address and hazard data for AI agents. Pay per call in USDC via x402.0stars
Lead Enrichment APIcompuute/lead-enrich-apiCurated EU AI/Sec/DevTools/Fintech B2B leads, Claude-scored. MCP+x402. Free 250/mo.0stars
Apollo Salesforce Mapperdev.workers.selbyventurecap.cf-worker/apollo-salesforce-mapperApollo->Salesforce Lead mapper. No LLM. Strict-fail required fields. PASS/REPAIR/FAIL verdict.0stars
Company Enrichment APIbr0ski777/company-enrichment-x402Company firmographics from domain: name, socials, tech stack, emails, phone, address0stars
HubSpotmindstone/mcp-serversHubSpot CRM: contacts, deals, tickets, line items, properties, marketing, files, workflows, threads0stars
FastMCP server for Apolloadelaidasofia/apollo-mcpFastMCP server for Apollo.io — 22 tools: sequences, campaign health, mailbox warmup, enrichment,…1stars