Infinite Context (ICX) MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ICX_SPACE_ID | No | Memory space partition namespace | default |
| ICX_LICENSE_KEY | No | Calera Labs API Key (obtain free at https://dashboard.caleralabs.com) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| icx_inspect_spaceA | Audits and retrieves real-time telemetry for a partitioned memory space (active node count, total synapses, grounded facts count, memory state, and contradiction alarms). Use this tool to monitor memory health, verify ingestion, or inspect space capacity. Read-only with no side effects. |
| icx_quote_slotA | Retrieves exact character-for-character verbatim text quotes from stored document registers by document family and ordinal slot index. Use this tool when exact contractual wording, legal clauses, or code revisions must be quoted without AI paraphrasing. Use icx_recall_scoped for semantic QA instead. Read-only with no side effects. |
| icx_recall_scopedA | Performs associative semantic recall across long-term memory to retrieve grounded facts, citations, and source documents matching a natural language question. Use this tool when answering questions about previously saved documents or facts (e.g. 'What is the pricing tier?', 'Who is the lead architect?'). If you only need raw keyword matching across entity names, use icx_search_facts instead. For character-exact verbatim quotes of stored documents, use icx_quote_slot. Read-only with no side effects. |
| icx_rememberA | Stores text, documents, code snippets, or conversational facts into long-term persistent memory for later retrieval across sessions. Ingests content into topological memory nodes with zero context window decay. Use this tool whenever you need to save facts, contracts, documentation, or user details for future reference. Do not use for querying existing memory (use icx_recall_scoped or icx_search_facts instead). Ingestion is additive and non-destructive. |
| icx_reset_sessionA | Resets conversational dialogue history for a session while strictly preserving all underlying crystallized knowledge, learned facts, and document weights in the memory space. Use when starting a new conversation topic while retaining all learned knowledge. Mutates session dialogue state but leaves persistent memory intact. |
| icx_search_factsA | Searches memory lattice nodes and decoded facts by keyword overlap and proximity across the active memory space. Use this tool for entity exploration or keyword discovery. For natural language question answering with grounded factual citations, use icx_recall_scoped instead. Read-only with no side effects. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Calera-Labs/icx-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server