Skip to main content
Glama

memory_ingest

Convert ephemeral insights into permanent long-term memory. Automatically chunks text, generates vector embeddings, and stores segments for semantic recall.

Instructions

Promote content into permanent long-term memory (demo.marsvault_chunks). Automatically chunks the input text, generates vector embeddings, and stores each segment for semantic recall. Use this to preserve important insights, decisions, patterns, or knowledge that should survive beyond the current session. This is the primary path from ephemeral to permanent memory.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dateNoDate for this content in YYYY-MM-DD format. Defaults to today if omitted.
tagsNoCategorization tags (e.g. ["decision", "architecture"])
typeNoContent type label (e.g. "insight", "observation", "decision")insight
originNoOrigin markerwarp-demo
contentYesThe insight content to promote to long-term memory. Be specific and self-contained — future recall depends on the quality of this text.
sectionNoOptional section label prefix to organize chunks within the source
agent_bodyNoThe persona/body this memory belongs to (e.g. "coco", "toto")
visibilityNoAccess level: "private" = this profile only, "shared" = cross-profile readable, "global" = system-wideprivate
environmentNoEnvironment label (e.g. "production", "staging")
source_fileNoLogical file path or identifier for the source (e.g. "sessions/2026-06-10-session-notes")
source_toolNoThe tool/platform where this insight was originally captured
max_chunk_charsNoMaximum characters per chunk (default 1200). Adjust for finer or coarser granularity.
source_memory_idNoLink this promotion to a specific short-term memory ID (for traceability)
source_user_noteNoBrief note explaining why this memory was selected for promotion
source_session_idNoSession ID where this insight originated (for provenance tracking)

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changedv0.1.3
    • changedInput schema / properties / source_tool / enum
      Previous value: -[
      -  "perplexity",
      -  "cursor",
      -  "warp",
      -  "openclaw",
      -  "hermes"
      -]New value: +[
      +  "perplexity",
      +  "cursor",
      +  "warp",
      +  "openclaw",
      +  "hermes",
      +  "draft",
      +  "grok"
      +]
  2. Changed14 schema fields changedv0.1.1
    • changedInput schema / properties / agent_body / description
      Previous value: -"Optional body label for memory boundary"New value: +"The persona/body this memory belongs to (e.g. \"coco\", \"toto\")"
    • changedInput schema / properties / content / description
      Previous value: -"Insight full text content"New value: +"The insight content to promote to long-term memory. Be specific and self-contained — future recall depends on the quality of this text."
    • changedInput schema / properties / date / description
      Previous value: -"Optional YYYY-MM-DD date override"New value: +"Date for this content in YYYY-MM-DD format. Defaults to today if omitted."
    • changedInput schema / properties / environment / description
      Previous value: -"Optional environment label"New value: +"Environment label (e.g. \"production\", \"staging\")"
    • addedInput schema / properties / max_chunk_chars / description
      Added value: +"Maximum characters per chunk (default 1200). Adjust for finer or coarser granularity."
    • changedInput schema / properties / section / description
      Previous value: -"Section label prefix"New value: +"Optional section label prefix to organize chunks within the source"
    • changedInput schema / properties / source_file / description
      Previous value: -"Logical source path for insight content"New value: +"Logical file path or identifier for the source (e.g. \"sessions/2026-06-10-session-notes\")"
    • changedInput schema / properties / source_memory_id / description
      Previous value: -"Optional short-memory id to link promoted long-memory chunks"New value: +"Link this promotion to a specific short-term memory ID (for traceability)"
    • changedInput schema / properties / source_session_id / description
      Previous value: -"Optional source session id for provenance"New value: +"Session ID where this insight originated (for provenance tracking)"
    • changedInput schema / properties / source_tool / description
      Previous value: -"Optional source tool for provenance"New value: +"The tool/platform where this insight was originally captured"
    • changedInput schema / properties / source_user_note / description
      Previous value: -"Optional user note describing why this memory was promoted"New value: +"Brief note explaining why this memory was selected for promotion"
    • changedInput schema / properties / tags / description
      Previous value: -"Optional tags list"New value: +"Categorization tags (e.g. [\"decision\", \"architecture\"])"
    • changedInput schema / properties / type / description
      Previous value: -"Chunk type"New value: +"Content type label (e.g. \"insight\", \"observation\", \"decision\")"
    • addedInput schema / properties / visibility / description
      Added value: +"Access level: \"private\" = this profile only, \"shared\" = cross-profile readable, \"global\" = system-wide"
  3. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses key behaviors: automatically chunks input, generates vector embeddings, stores each segment. No annotations exist, so the description carries full burden and does well.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences, front-loaded with the core action. Every sentence adds value without waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and 15 parameters with 100% schema coverage, the description covers the tool's purpose and process well. Could mention return value but not strictly necessary.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds minor extra context (e.g., 'Be specific and self-contained' for content) but does not significantly enhance beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Promote content into permanent long-term memory' with specific verb and resource. Distinguishes from siblings by calling it 'the primary path from ephemeral to permanent memory'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says to use for preserving important insights, decisions, patterns, or knowledge. Provides context but no explicit alternatives or when-not-to-use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Latest Blog Posts

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/Marsmanleo/MarsNMe'

If you have feedback or need assistance with the MCP directory API, please join our Discord server