memorycontextreasoningtruthfulnessorchestration
MCP server with 37 tools for session memory, context health, reasoning, and truthfulness verification using tiered memory storage.
Quick Install
Automated & IDE SetupCopy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
We couldn’t automatically confirm this listing starts correctly
We ran the install command below but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.
npx -y context-first-mcpNo response to initialize.
This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 1mo ago.
Manual Client & Custom JSON ConfigExpand JSON ▾
Client Config & Setup
Choose your client or environment
Target File:
💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Overview
Use cases
Maintain conversation context coherence over long interactions
Detect and resolve conflicting or ambiguous user inputs
Verify tool output correctness against intended goals
Manage persistent memory with state locking and recall
Orchestrate multi-tool workflows for advanced reasoning
Key features
37 research-backed tools organized in 7 functional layers
Unified context_loop orchestrator for single-call multi-tool execution
Context health monitoring including drift, ambiguity, and entropy checks
Truthfulness verification with conflict detection and self-critique
Persistent memory management with state locking and history summarization
Sandboxing tools for isolated sub-task memory silos
Capabilities & Tool Schemas (36)
Inspect callable tools, capabilities, and parameters exposed to AI agents by Context First MCP.
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
recap_conversationExtracts hidden intent, key decisions, and produces consolidated state summaries
detect_conflictsCompares new input against ground truth; surfaces contradictions
check_ambiguityIdentifies underspecified requirements and generates clarifying questions
verify_executionValidates whether tool outputs actually achieved the stated goal
entropy_monitorProxy-entropy scoring via lexical diversity, contradiction density, hedge frequency, and n-gram repetition (ERGO)
Documentation Overview
Context-First MCP
The MCP server that keeps your AI grounded, coherent, and honest — across every turn.
Works instantly with Claude Desktop · Cursor · VS Code · any MCP client · Vercel remote — zero API keys needed.
37 research-backed tools across 7 layers — context health, state, sandboxing, persistent memory, advanced reasoning, truthfulness verification, orchestration, structured research, and autonomous file export. One
context_loopcall replaces 6–7 individual tools and returns a unified action directive.
Why Your AI Conversations Break Down
Long AI conversations fail in predictable ways. Context-First fixes all four:
| Failure Mode | What Goes Wrong | Context-First Solution |
|---|---|---|
| Context Drift | AI forgets earlier decisions and intent as the conversation grows | context_loop + detect_drift continuously re-anchor every turn |
| Silent Contradiction | New inputs silently overrule established facts — the AI doesn't notice | detect_conflicts compares every input against locked ground truth |
| Vague Execution | AI proceeds on underspecified requirements, producing misaligned output | check_ambiguity + abstention_check ask clarifying questions instead of guessing |
| Hallucinated Success | Tool outputs look successful but didn't actually achieve the goal | verify_execution rechecks whether the outcome matches the stated intent |
What You Get
37 production-ready tools grouped into 7 layers — plus 1 orchestrator that runs them all:
One call. One directive. One score.
Quick Start
npx — zero install
Claude Desktop
Cursor / VS Code
Remote (Streamable HTTP)
Deploy your own Vercel instance
Tool Reference
Layer 1: Core Context Health (9 tools)
| Tool | Purpose |
|---|---|
context_loop | 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 |
recap_conversation | Extracts hidden intent, key decisions, and produces consolidated state summaries |
detect_conflicts | Compares new input against ground truth; surfaces contradictions |
check_ambiguity | Identifies underspecified requirements and generates clarifying questions |
verify_execution | Validates whether tool outputs actually achieved the stated goal |
entropy_monitor | Proxy-entropy scoring via lexical diversity, contradiction density, hedge frequency, and n-gram repetition (ERGO) |
abstention_check | 5-dimension confidence scoring — abstains with questions rather than hallucinating (RLAAR) |
detect_drift | Detects conversation drift from the original intent |
check_depth | Evaluates response depth against question complexity |
Layer 1b: State Management (4 tools)
| Tool | Purpose |
|---|---|
get_state | Retrieve confirmed facts and task status |
set_state | Lock in ground truth — subsequent conflict checks run against these values |
clear_state | Reset specific keys or all state |
get_history_summary | Compressed conversation history with intent annotations |
Layer 2: Sandbox & Discovery (3 tools)
| Tool | Method | Purpose |
|---|---|---|
discover_tools | MCP-Zero + ScaleMCP | Natural-language tool routing — returns only semantically relevant tools, reducing context bloat by up to 98% |
quarantine_context | Multi-Agent Quarantine | Create isolated memory silos for sub-tasks, preventing intent dilution |
merge_quarantine | Multi-Agent Quarantine | Merge silo results with noise filtering — only promoted keys return to main context |
Layer 3: Persistent Memory (6 tools)
| Tool | Purpose |
|---|---|
memory_store | Store findings, decisions, and intermediate results with metadata |
memory_recall | Retrieve relevant memories by semantic query |
memory_compact | Compress and consolidate memory entries |
memory_graph | Build and query a knowledge graph from stored memories |
memory_inspect | Inspect memory store contents and statistics |
memory_curate | Deduplicate and organize memory entries |
Layer 4: Advanced Reasoning (5 tools)
| Tool | Method | Purpose |
|---|---|---|
inftythink_reason | InftyThink | Infinite-depth reasoning with adaptive stopping |
coconut_reason | Coconut | Chain-of-Continuous-Thought in latent space |
extracot_compress | ExtraCoT | Compress chain-of-thought while preserving reasoning fidelity |
mindevolution_solve | MindEvolution | Evolutionary search over the solution space |
kagthinker_solve | KAG-Thinker | Knowledge-augmented generation with structured thinking |
Layer 5: Truthfulness & Verification (7 tools)
| Tool | Purpose |
|---|---|
probe_internal_state | Probe model consistency across paraphrased prompts |
detect_truth_direction | Detect whether model reasoning is trending toward or away from truth |
ncb_check | Neighborhood consistency check across semantically equivalent inputs |
check_logical_consistency | Verify logical coherence of reasoning chains |
verify_first | Pre-verification before committing to claims |
ioe_self_correct | Intrinsic-extrinsic self-correction |
self_critique | Structured self-critique with improvement suggestions |
Research Pipeline & Export (2 tools)
| Tool | Purpose |
|---|---|
research_pipeline | Structured research orchestration across init → gather → analyze → verify → finalize. Covers all 34 underlying tool-equivalents — state, sandboxing, memory, reasoning, truthfulness, context health. Writes files autonomously to disk as the pipeline runs; no LLM cooperation needed for file output. |
export_research_files | Writes every verified report chunk and/or every raw evidence batch to disk in a single call. |
Built on Peer-Reviewed Research
Every core algorithm traces back to a published paper:
| Algorithm | Paper | arXiv | Tool |
|---|---|---|---|
| MCP-Zero | Active Tool Request | 2506.01056 | discover_tools |
| ScaleMCP | Semantic Tool Grouping | 2505.06416 | discover_tools registry |
| ERGO | Entropy-based Quality | 2510.14077 | entropy_monitor |
| RLAAR | Calibrated Abstention | 2510.18731 | abstention_check |
Implementation highlights:
- Proxy Entropy (ERGO): 4 response-level proxy signals (lexical diversity, contradiction density, hedge-word frequency, n-gram repetition) replace inaccessible token-level logprobs. Composite score above threshold triggers adaptive context reset.
- TF-IDF Discovery (MCP-Zero): Pure TypeScript, zero external dependencies. Indexes all tool descriptions at startup; cosine similarity routes queries to the top-k relevant tools only.
- Inference-Time Abstention (RLAAR): 5-dimension confidence scoring replaces the RL training loop. Abstains with targeted questions when confidence < threshold — no hallucination fallback.
Export Helper (1 tool)
| Tool | Description |
|---|---|
export_research_files | Writes research artifacts directly to disk. It can automatically expand and write every verified report chunk without asking the LLM to loop finalize manually, and it can also write every gathered raw-evidence batch even when verify has not passed. |
context_loop Pipeline
Related MCP Servers
Adoption & maintenance
Factual signals from GitHub, npm, and our automated checks — not a rating.
GitHub stars
1
Stargazers on the source repository.
Last commit
5mo ago
Most recent push to the default branch.
Install check
Inconclusive
Didn't respond in our test window — often a slow first install.
Tools exposed
36
Callable tools this server registers over MCP.
Directory activity
2 views
Config copies, upvotes, and views on AllMCPs.
Reviews
No reviews yet — be the first to share how this listing worked for you.
Frequently Asked Questions about Context First MCP
AllMCPs Directory Badge
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
Badge Style:
Live Dynamic SVG Preview
Markdown (GitHub README)
[](https://allmcps.com/mcp/xjtlumedia-context-first-mcp)HTML Embed
<a href="https://allmcps.com/mcp/xjtlumedia-context-first-mcp"><img src="https://allmcps.com/api/badge/xjtlumedia-context-first-mcp?style=directory" alt="Context First MCP on AllMCPs" /></a>