Prototyp · Vorschau: alle Server aus der offiziellen Registry, alle 30 Minuten synchronisiert. Bewertungen und Benutzerkonten folgen in einem späteren Schritt.
PopNx MCPMCP-Server für alle, die KI nutzen · in einfachen Worten erklärt

Calera Infinite Context (ICX) — Persistent Memory & Associative Recall

von Calera-LabsVersion 1.4.0i★ –iLäuft in der Cloud
Name in der Registryio.github.Calera-Labs/icx-mcp

Installieren

Überblick

Beschreibung vom Entwickler (englisches Original)

Sub-5ms topological 4D associative memory coprocessor for LLMs and multi-agent swarms.

Die drei Säulen von PopNx MCP

Diese drei werden nie zu einer Punktzahl zusammengefasst: Meinungen, Messungen und Beliebtheit sind verschiedene Dinge.

Was du damit machen kannst

Für diesen Server haben wir noch keine Zusammenfassung in einfacher Sprache geschrieben. Unten stehen die Fakten, die wir aus der Registry gelesen haben.

  • Verbindung: Läuft in der Cloud
  • Transport: Streamable HTTP
  • Kategorie: Suche & KI-Gedächtnis
  • Das musst du eintragen: X-License-Key

Installation

Wähle die KI-App, die du nutzt, und kopiere die Einstellungen.

Bevor du installierst

  • Basischecks: 3 von 3 bestanden
  • Läuft auf dem Server des Entwicklers: Was du fragst, läuft über dessen Server.
  • Kann 25 Dinge (Tools) claim_1m_nodes, dispatch_actuation, icx_exec, icx_get_connector_document …
  • Das trägst du selbst ein: X-License-Key, X-Space-ID

Als geheim markierte Werte sind Schlüssel zu deinem Konto. Gib sie nie weiter und füge sie nie in einen Chat ein.

Du brauchst

Welche App nutzt du?

Wähle oben deine App. Wir merken sie uns, damit der Button beim nächsten Mal „In … installieren“ anzeigt.

Diese Adresse braucht einen Schlüssel in einem Header der Anfrage, und das Menü zum Hinzufügen von Connectors kann ihn nicht setzen. Nutze stattdessen Claude Code, Cursor oder VS Code.

Führe das in deinem Terminal aus

claude mcp add --transport http icx https://icx.caleralabs.com/mcp --header 'X-License-Key: your-value' --header 'X-Space-ID: your-value'

Trag die leeren Werte ein, bevor du ihn startest.

In Cursor öffnen

Oder kopier die Einstellungen selbst

In .cursor/mcp.json in deinem Projekt oder in ~/.cursor/mcp.json einfügen

{
  "mcpServers": {
    "icx": {
      "url": "https://icx.caleralabs.com/mcp",
      "headers": {
        "X-License-Key": "your-value",
        "X-Space-ID": "your-value"
      }
    }
  }
}

Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.

In VS Code öffnen

Oder kopier die Einstellungen selbst

In .vscode/mcp.json in deinem Projekt einfügen

{
  "servers": {
    "icx": {
      "type": "http",
      "url": "https://icx.caleralabs.com/mcp",
      "headers": {
        "X-License-Key": "your-value",
        "X-Space-ID": "your-value"
      }
    }
  }
}

Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.

Diese Adresse braucht einen Schlüssel in einem Header der Anfrage, und das Menü zum Hinzufügen von Connectors kann ihn nicht setzen. Nutze stattdessen Claude Code, Cursor oder VS Code.

Deine Auswahl bleibt in einem Cookie auf diesem Gerät; kein Konto nötig.

Werte, die du selbst einträgst

  • X-License-Key geheim erforderlich HTTP header
    Calera Labs API Key (obtain free at https://dashboard.caleralabs.com)
  • X-Space-ID HTTP header
    Memory partition namespace (default: 'default')

Diese Einstellungen werden aus dem Registry-Eintrag des Entwicklers erzeugt. Wenn in der README etwas anderes steht, folge der README.

Was er kann

Tool-Namen und -Beschreibungen genau so, wie der Server sie am 7. Nov. 2026 gemeldet hat. Geschrieben hat sie der Entwickler, nicht wir; wir zeigen sie als reinen Text.

  • claim_1m_nodes

    The calling agent completes free signup itself. Claims a permanent 1,000,000-node Epistemic Memory Vault at $0. Pass principal_email and accept_a2b_terms=true. Email is enough. Google sign-in is not required.

  • dispatch_actuation

    Vaulted, policy-gated actuation into external tools (GitHub, GitLab, Slack, Jira, Linear, Postgres) with child-node crystallization in e.mem.

  • icx_exec

    Executes programmatic Python code inside a sandboxed execution runtime with direct sub-5ms native access to persistent Volumetric Lattice Network memory via the global 'icx' object (icx.search, icx.recall, icx.quote, icx.remember, icx.stats, icx.contradictions). Use this tool for

  • icx_get_connector_document

    Retrieves the full on-demand text, markdown, or code content of a connected document, file, page, or issue from external services (Google Drive doc, Notion page, GitHub file, GitLab file, Linear ticket). Read-only operation. Requires X-License-Key authentication.

  • icx_inspect_connector_facts

    Inspects the active grounded facts and simplicial statements currently tracked in Volumetric Memory for a specific connector or data source. Read-only operation. Requires X-License-Key authentication.

  • icx_inspect_space

    Audits and returns real-time diagnostic telemetry for a partitioned memory space, including active node counts, total synapses, grounded facts, memory state, and contradiction alarms. Use this tool to monitor memory partition health, verify document ingestion, check storage capac

  • icx_list_connectors

    Lists all active cloud changefeed connectors (GitHub, GitLab, Notion, Google Drive, Linear, Slack, PostgreSQL) registered for the tenant. Read-only operation. Requires X-License-Key authentication.

  • icx_multihop_walk

    Executes a single-pass sub-5ms multi-hop simplicial causal walk across the Volumetric Lattice Network and Ontology relations. Traces transitive dependency chains (e.g. A -> B -> C -> D -> Leaf) and resolves temporal state overrides (retaining dynamic multi-policy mutations). Read

  • icx_purge_source

    Executes O(1) instant memory unlinking and revocation of all facts, simplices, and document associations learned from a specific data source or connector without requiring model retraining. Mutating operation. Requires X-License-Key authentication.

  • icx_quote_slot

    Retrieves exact character-for-character verbatim text and cryptographic SHA-256 hashes from document registers by document family and 1-based slot index without AI paraphrasing. Optional start (0-based character offset) and length (character count) return a verbatim slice of the

  • icx_recall_scoped

    Performs semantic search across persistent long-term memory to retrieve grounded facts, relevant citations, and source documents matching a natural language question. Use this tool when answering questions about previously saved project specifications, codebase decisions, user pr

  • icx_register_connector

    Registers a new cloud webhook changefeed connector or remote MCP server for continuous epistemic auto-sync with AES-256-GCM secret vaulting and HMAC signature verification. Mutating operation. Requires X-License-Key authentication.

  • icx_remember

    Stores text documents, code snippets, architectural decisions, and factual knowledge into persistent long-term memory partitioned by space_id. Use this tool when saving important facts, project conventions, API keys, user preferences, or documentation for future sessions. Do NOT

  • icx_reset_session

    Clears conversational dialogue turn history for a session while strictly preserving all underlying persistent memory, learned facts, and document registers in the memory space. Use this tool when switching conversation topics or clearing dialogue context between independent tasks

  • icx_search_facts

    Performs keyword and token search across persistent memory to discover entities, names, and matching terms within a memory space. Use this tool for entity exploration, keyword discovery, and locating specific identifiers or variables in memory. Do NOT use for answering natural la

  • icx_swarm_state

    Manages the persistent shared variable namespace (V_t) and mutex leases for collaborative swarms of autonomous agents (Cursor, Claude, Cline, OpenDevin). Reads, writes, or atomic CAS-swaps typed state objects (AST graphs, data tables, audit flags) without prompt re-serialization.

  • icx_sync_audit

    Retrieves historical synchronization events, deltas processed, facts learned, and sub-2ms latency telemetry for compliance and audit auditing. Read-only operation. Requires X-License-Key authentication.

  • icx_sync_delta

    Extracts fine-grained deltas between previous text/document state and updated state, and crystallizes them into the Volumetric Memory lattice in sub-2ms on CPU with automatic secret scrubbing and SHA-256 deduplication. Use this tool for continuous incremental sync of code files,

  • icx_trigger_sync

    Triggers an on-demand active pull and delta synchronization for a registered connector (GitHub, GitLab, Notion, Google Drive, Linear, Slack, PostgreSQL). Fetches live commits, issues, PRDs, or DDL schemas and crystallizes deltas into persistent Volumetric Memory in sub-2ms. Mutat

  • icx_var_get

    Retrieves a named typed variable, AST, symbol table, or state object from the persistent V_t swarm namespace. Read-only. Requires X-License-Key authentication.

  • icx_var_list

    Lists all active variables and types stored in the persistent V_t swarm namespace, with optional prefix matching. Read-only. Requires X-License-Key authentication.

  • icx_var_set

    Stores a named typed variable, AST, symbol table, or state object into the persistent V_t swarm namespace with optional TTL. Accessible to all collaborative agents. Requires X-License-Key authentication.

  • icx_wasm_exec

    Executes compiled WebAssembly (WASM) bytecode or WAT text in-process with direct sub-100 microsecond Go host function memory bindings (icx_search, icx_recall, icx_quote, icx_remember, icx_walk, icx_get_var, icx_set_var, icx_stats). Eliminates subprocess spawning and socket IPC fo

  • recall_epistemic_context

    Sub-5ms Voronoi topological walk and semantic recall across connected tools, repos, issues, and memory. Replaces external read tools.

  • solve_hermeneutics

    Public Deterministic Solver for Comparative Paradigmatic Analysis (CPA), 1st-Century Jewish Hermeneutics (Middot), and Concentric Chiastic Folding for Tov Rose and Dr. Pitcher research. Zero hallucination guarantee (boundary operator d^2 = 0).

Basischecksi

Wir prüfen Informationen, die jeder sehen kann; den Code haben wir nicht gelesen. Checks, die nicht zutreffen, werden nicht mitgezählt. · Geprüft am 8. Nov. 2026

  • ✓ Bestanden

    Entwickler passt zum Repo

    Der Registry-Name wurde mit dem GitHub-Konto Calera-Labs bestätigt, dem das Repo gehört

  • … Noch nicht geprüft

    Wird noch gepflegt

    Dieses Repo haben wir noch nicht von GitHub gelesen

  • … Noch nicht geprüft

    Hat eine Lizenz

    Dieses Repo haben wir noch nicht von GitHub gelesen

  • ✓ Bestanden

    Endpunkt antwortet

    Antwort in 192 ms (HTTP 200)

  • – Nicht zutreffend

    Anmeldung mit OAuth

    Keine Anmeldung nötig

  • ✓ Bestanden

    Keine versteckten Anweisungen in Tool-Beschreibungen

    Wir haben 25 Tool-Beschreibungen gelesen und keine versteckten Anweisungen an die KI gefunden

Im Vergleich mit anderen in Suche & KI-Gedächtnisi

  • Mehr Sterne als 0 % der anderen 5714 Server in dieser Kategorie
  • Neuer in der Registry veröffentlicht als 75 % der anderen 5714 Server in dieser Kategorie
  • Basischecks gleich gut wie oder besser als bei 100 % der anderen 5714 Server in dieser Kategorie

Verglichen mit allen aktiven Servern dieser Kategorie in der Registry. Sterne zählen nur, wenn dem Herausgeber das Repo gehört.

Häufige Fragen

Ist Calera Infinite Context (ICX) — Persistent Memory & Associative Recall sicher?

Er hat 3 von 3 zutreffenden Basischecks bestanden. Den Code haben wir nicht gelesen. Bevor du einen Schlüssel oder Token hinzufügst, sieh nach, welche Zugriffe der Server verlangt, und nutze einen Schlüssel, der nur die Berechtigungen hat, die du brauchst.

Welche Schlüssel oder Codes braucht er?

Das musst du eintragen: X-License-Key

Läuft er auf meinem Computer oder in der Cloud?

Er läuft in der Cloud des Entwicklers. Du verbindest dich übers Internet, ohne etwas zu installieren, aber was du sendest, läuft über die Server des Entwicklers.

Wird er noch gepflegt?

Das GitHub-Repo wurde zuletzt – geändert, und die neueste Version (1.4.0) kam vor 13 Tagen in die Registry.

Welche Apps können ihn nutzen?

Apps, die MCP unterstützen, etwa Claude Desktop, Claude Code, Cursor und VS Code. Er verbindet sich per URL, also funktionieren auch Apps, die Remote-MCP-Server akzeptieren, zum Beispiel ChatGPT im Entwicklermodus.

Was kann ich stattdessen nutzen?

In derselben Kategorie: Context7, Codebase Memory, Exa

Alternativen

Server derselben Kategorie von anderen Entwicklern, sortiert nach Sternen.

So liest du eine Karte:↓ Downloads pro Wochei★ GitHub-SterneiDrei Säulen: Bewertungen · Checks · NutzungiAktualisiert = neueste Version in der Registry veröffentlichti

Context7

Up-to-date docs for AI agents

von upstashWeit verbreitet↓ 972.664/Wo.★ 64.224Aktualisiert vorgestern

Computer oder Cloud

Codebase Memory

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

von DeusDataWeit verbreitet↓ 17.962/Wo.★ 48.148Aktualisiert vor 22 Tagen

Läuft auf deinem Computer

Exa

Connect AI agents to Exa for web search, content fetching, and multi-step research.

von exa-labsWeit verbreitet★ 5213Aktualisiert vor 2 Monaten

Läuft in der Cloud✓ exa.ai

README vom Entwickler

README öffnen

Unverändert aus dem Repo des Entwicklers übernommen. PopNx MCP hat den Inhalt weder geprüft noch empfiehlt es ihn. HTML, Bilder und Skripte wurden entfernt. Links führen von dieser Website weg.

Infinite Context (ICX) — Persistent Memory MCP Server

-emerald.svg)

Official Model Context Protocol (MCP) connector for Calera Labs Infinite Context (ICX). Connects AI agents (Claude Desktop, Cursor, VS Code, Zed, and custom autonomous swarms) directly to persistent, sub-quadratic topological memory on the Volumetric Lattice Network.

"Context Without Limits. Memory Without Loss."


⚡ Why ICX Over Naive 1M+ Context Windows?

  • Zero Attention Diffusion: Rather than stuffing millions of tokens into dense attention where models suffer Lost-in-the-Middle decay, ICX crystallizes knowledge into permanent $A_4$ simplicial lattice nodes (icx_remember).
  • Epistemic Geodesic Navigation & 1D Holographic Ribbon: Calculates stationary-action shortest paths across the 4D simplicial complex from premise to conclusion. Replaces noisy 2,000+ token context bags with an 80-token crystal chain ( ), reducing prompt injection tokens and Time-To-First-Token (TTFT) by >40%.
  • Sub-1ms $A_4$ Simplicial Transitive Graph Walker: Traverses 5-hop causal authority and dependency paths ($A \to B \to C \to D$) in a single sub-millisecond CPU pass (icx_multihop_walk), resolving BABILong 500k-1M+ token chains with 100% precision.
  • Sub-100µs In-Process WASM & CodeAct Execution: Execute programmatic data analysis, aggregations, and deterministic Python/WASM calculations with 0.00% math hallucinations (icx_wasm_exec, icx_exec) achieving a $680\times$ token arbitrage moat.
  • Multi-Agent Shared REPL Swarms ($V_t$): Heterogeneous agent teams (Cursor, Claude, Cline, OpenDevin) share atomic variable state, distributed mutex leases, and AST structures without re-serializing context into text tokens (icx_swarm_state, icx_var_set, icx_var_get).
  • 2026-07-28 Stateless Protocol Core: Fully compliant with the 2026-07-28 Stateless MCP Specification (SEP-2243, SEP-2575, SEP-2549) with sub-5ms zero-handshake direct tool calls and intelligent caching (ttlMs: 86400000).
  • 100% Sweep on Major Public Benchmarks:
  • 96.28% (466/484 exact) on RULER MRCR v2 at 128k–1M context (and 100.00% on 10M NIAH / BenchLM 1M single-needle).
  • 100.00% on BABILong 500k 5-hop causal resolution in 882µs.
  • 100.00% on $\tau$-bench multi-policy retention.
  • 99.76% cost & token savings on Artificial Analysis evaluation.
  • 1.0 Grounding Score on SWE-bench AST symbol fidelity.
  • Streamable Hosted Endpoint: Zero local model downloads required. Connect via streamable HTTP/SSE with your API key from dashboard.caleralabs.com.

🚀 1-Click Quickstart Integrations

1. Cursor IDE

Add the following to your project's .cursor/mcp.json (or global Cursor Settings → Features → MCP):

{

"mcpServers": { "infinite-context": { "url": "https://icx.caleralabs.com/mcp", "headers": { "X-License-Key": "clabs_live_YOUR_KEY", "X-Space-ID": "default" } } } }

*(Get your free API key at [dashboard.caleralabs.com](https://dashboard.caleralabs.com))*

2. Claude Desktop

Add to your claude_desktop_config.json:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json
{

"mcpServers": { "infinite-context": { "url": "https://icx.caleralabs.com/mcp", "headers": { "X-License-Key": "clabs_live_YOUR_KEY" } } } }


3. Smithery CLI (1-Click Terminal Command)

Install automatically across Claude, Cursor, or VS Code using Smithery:

# For Claude Desktop

npx -y @smithery/cli install @calera-labs/icx-mcp --client claude

For Cursor IDE

npx -y @smithery/cli install @calera-labs/icx-mcp --client cursor

For VS Code

npx -y @smithery/cli install @calera-labs/icx-mcp --client vscode


4. VS Code / GitHub Copilot

Add to .vscode/mcp.json:

{

"servers": { "infinite-context": { "url": "https://icx.caleralabs.com/mcp", "headers": { "X-License-Key": "clabs_live_YOUR_KEY" } } } }


5. Stdio Gateway Proxy (Air-Gapped / CLI)

If your environment only supports local stdio sub-processes:

{

"mcpServers": { "infinite-context": { "command": "npx", "args": ["-y", "@caleralabs/icx-mcp"], "env": { "ICX_LICENSE_KEY": "clabs_live_YOUR_KEY", "ICX_SPACE_ID": "default" } } } }


6. Zero-Config Auto-Bridge with Calera LLM-VM (@caleralabs/llm-vm-mcp)

Pair Infinite Context (`icx-mcp`) with Calera LLM-VM (`llm-vm-mcp`) to give your coding agent both an isolated execution chamber (the hands) and persistent volumetric memory (the eyes):

{

"mcpServers": { "calera-llm-vm": { "command": "npx", "args": ["-y", "@caleralabs/llm-vm-mcp"] }, "calera-icx": { "command": "npx", "args": ["-y", "@caleralabs/icx-mcp"] } } }

  • Zero-Setup Auto-Bridge: Both servers share ~/.calera/icx.env and bind to the exact same deterministic space ID (space_ ).
  • Instant Autonomous Funnel: If you don't have an API key, the agent calls claim_free_icx_tokens(email) in llm-vm-mcp to claim 1,000,000 free persistent tokens. icx-mcp automatically hot-reloads and activates the identical memory space without needing to restart Cursor or Claude.
  • Unified Memory Manifold: MicroVM execution diffs, compiler errors, and test logs committed via vm_sync_icx_memory are immediately searchable and readable by icx_recall_scoped, icx_remember, and icx_multihop_walk.

🛠️ Certified MCP Tools Reference (19 Tools)

ToolPurposePrimary InputsBehavior
`icx_remember`Stores text, code, decisions, and documentation into persistent long-term memory.text (required), space_id, filename, familyAdditive & Non-destructive
`icx_recall_scoped`Performs semantic search across memory to retrieve grounded facts and source citations for QA. Supports optional format: "ribbon" for 1D Geodesic Ribbon prompt injection.query (required), space_id, top_k, format (optional: standard \ribbon)Read-only
`recall_epistemic_context`Ultra-compact (<160 tokens) read gateway into persistent epistemic memory. Returns high-salience grounded facts with optional 1D holographic ribbon serialization (format: "ribbon").query (required), space_id, top_k, format (optional: standard \ribbon)Read-only
`icx_search_facts`Keyword and entity search across memory nodes for lexical exploration and token lookup.query (required), space_id, limitRead-only
`icx_quote_slot`Retrieves exact character-for-character verbatim text and SHA-256 hashes from document registers.family (required), index (required), space_idRead-only
`icx_inspect_space`Returns diagnostic telemetry: active nodes, total synapses, grounded facts, and contradiction alarms.space_id (optional)Read-only
`icx_reset_session`Clears conversational turn history while preserving all underlying persistent memory.space_id (optional)Mutates session only
`icx_sync_delta`Extracts fine-grained text/JSON deltas and crystallizes them into the lattice in sub-2ms on CPU.new_text (required), old_text, uri, source_id, space_idMutating Sync
`icx_list_connectors`Lists all active continuous changefeed connectors (GitHub, GitLab, Notion, Drive, Linear, Slack, SQL).*None*Read-only
`icx_register_connector`Registers a new cloud webhook changefeed connector with AES-256-GCM secret vaulting.type (required), name (required), target_uri (required), webhook_secretMutating Sync
`icx_purge_source`Executes O(1) instant memory unlinking and revocation of all facts from a source without retraining.source_id (required), space_idMutating Purge
`icx_sync_audit`Retrieves historical delta synchronization events, deltas processed, facts learned, and latency metrics.*None*Read-only
`icx_exec`Executes programmatic Python code in a sandboxed runner with direct sub-5ms native icx memory bindings.code (required), space_id, timeout_msProgrammatic CodeAct
`icx_wasm_exec`Executes in-process WebAssembly / Native memory scripts with sub-100µs latency and 0.00% math error.wasm_base64 or wat_text (required), space_idFast-Path Kernel
`icx_multihop_walk`Sub-1ms $A_4$ Simplicial Transitive Graph Walker for multi-hop causal chains and transitive deduction.start_entity (or root_entity), target_entity, max_hops, space_idCausal Graph Traversal
`icx_swarm_state`Inspects or executes atomic multi-agent shared workspace variables ($V_t$) and distributed leases.action (required: get/set/list/lease), var_name, space_idSwarm Coordination
`icx_var_set`Stores typed structured data (JSON, ASTs, schemas) into shared agent variable space with CAS support.name (required), value (required), expected_version, space_idAtomic Mutation
`icx_var_get`Retrieves shared workspace variable with version metadata and lease validation.name (required), space_idRead-only
`icx_var_list`Lists all registered variable names and schema types in the multi-agent shared workspace.space_id (optional)Read-only

🧭 Epistemic Geodesic Navigation & 1D Holographic Ribbon Mode

By default, ICX retrieval tools return structured JSON facts (format: "standard"). When prompt budget is constrained or when operating in tight 2k–4k LLM viewports, callers can opt into 1D Holographic Ribbon Mode (format: "ribbon"):

MCP Tool Call Example:
{

"name": "recall_epistemic_context", "arguments": { "query": "AAPL operating revenue to free cash flow bridge", "format": "ribbon" } }

Serialized Holographic Ribbon Output:
<nav:ribbon premise="AAPL_REV" target="FREE_CASH_FLOW" steps=4 action=5.6600>

AAPL_REV -> OPERATING_INCOME -> TAX_EXPENSE -> NOPAT -> FREE_CASH_FLOW

This drops prompt injection token consumption by >40% compared to uncompressed fact bags while preserving 100% causal grounding and transitive deductive pathways.


🤖 Recommended Agent System Instruction

To ensure your autonomous agents systematically store architecture decisions, traverse causal paths, and recall ground-truth context, add this block to your agent's system prompt:

1. Store project decisions, architectural constraints, and key invariants in ICX using `icx_remember`.
  1. Before answering historical codebase questions or resolving complex dependencies, use icx_recall_scoped or icx_multihop_walk to retrieve exact grounded facts and transitive causal chain

Nur der Anfang wird gezeigt; den Rest findest du im Repo

PopNx fragen