Memory MCP

ingest_conversation

Distills raw conversations or dense text into clean, deduplicated facts and stores them as project memory, so long transcripts and generated plans become reusable knowledge.

Instructions

Distill a raw conversation or dense text into clean facts and store them.

When to use this tool

Use this when a large block of text needs to be turned into memory:

The user pastes a meeting transcript, chat log, or design doc.
You just generated a dense response (e.g. a full architecture plan, a multi-module breakdown, a deployment strategy) that contains many facts worth remembering. Pass your own response text into this tool.
The user asks you to "remember this" or "save this" about a big block.
Rule of thumb: if the text contains more than ~3 distinct facts, use this tool instead of calling remember many times.

What happens internally

Memory MCP's backend uses a dedicated extraction LLM to read the full text (both user and assistant turns), extract only the durable conclusions, standardise them into clean facts with conflict keys, and deduplicate against existing memory. Dead ends, chit-chat, and corrected mistakes are discarded automatically.

How to resolve the project_name

Same as remember: auto-match if unambiguous. If ambiguous, call list_projects() and explicitly ask the user to choose. Once chosen, session-lock it.

Args: conversation: The raw text to distill — can be a chat transcript, your own generated response, meeting notes, or any unstructured text. project_name: Project name. If provided, facts are stored under that project. If omitted, stored as global. tool: Calling tool name (for audit + provenance).

Returns counts of extracted/created/merged/superseded facts.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "conversation": "<conversation>"
    },
    "name": "ingest_conversation"
  }
}

Input Schema

Name	Required	Default
`tool`	No	unknown
`conversation`	Yes
`project_name`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 31, 2026

TDQS

A4.7/5.0

Behavior4/5

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses the internal extraction LLM, deduplication against existing memory, conflict keys, discarding of dead ends and corrections, and returned counts of extracted/created/merged/superseded facts. It does not mention permissions, rate limits, or reversibility, which keeps it from a 5 for a write-oriented memory tool.

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

Conciseness4/5

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

The description is front-loaded with purpose and usage guidance, then uses clear headings for internal behavior and project resolution. It is longer than minimally necessary, but the length is largely justified by the complexity and the 0% schema coverage; remaining verbosity is mild rather than wasteful.

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

Completeness5/5

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

This is a complex ingestion tool with no annotations and an output schema present, so the description needs to cover selection, behavior, and parameters. It does so thoroughly, including when to prefer it over `remember`, what happens internally, how project scoping works, and what kind of counts are returned.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must compensate, and it does. It explains `conversation` as raw text ranging from transcripts to the assistant's own generated response, clarifies that omitting `project_name` stores facts globally, and identifies `tool` as the calling tool name used for audit and provenance.

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?

The description states a specific verb and resource: distill raw conversation or dense text into clean facts and store them. It also distinguishes this tool from the sibling `remember` by setting a threshold of more than roughly three distinct facts, so an agent can choose between them without opening either schema.

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

Usage Guidelines5/5

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

It explicitly lists when to use the tool with concrete examples such as meeting transcripts, chat logs, design docs, and the assistant's own dense responses. It also names the alternative (`remember`) for smaller fact sets and explains how to resolve `project_name`, including calling `list_projects()` when ambiguous.

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

Deploy Server