Skip to main content
Glama
madgodinc

mgi-mind

Official
by madgodinc
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

mind_ingest

Write approved memory, facts, and procedures into a library with secret scrubbing and duplicate checks; omit candidates to extract from raw text.

Instructions

Auto-ingest memory. PRIMARY: pass a candidates array of already-extracted items you judged worth keeping. BACKSTOP: omit candidates and pass raw text for marker-based heuristic extraction. Each candidate is secret-scrubbed and near-dup-checked before writing.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
rawNoRaw text for heuristic extraction (used only when candidates is omitted)
libraryNoTarget library for memory candidates. Pass the library of the PROJECT this content is about (e.g. its project name) — most mgi-mind instances split memory by project, and 'projects' is the catch-all for cross-project or unclassified notes, not a safe generic choice. The default exists so the call doesn't fail when omitted, not as a recommendation; look up the right library (mind_context or mind_search) before relying on it.projects
candidatesNoExtracted items. Each is one of: {"type":"memory","content":"..."} | {"type":"fact","subject":"...","predicate":"...","object":"..."} | {"type":"procedure","trigger_error":"...","fix":"..."}

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It usefully discloses that each candidate is secret-scrubbed and near-dup-checked before writing, implying a write operation and some safety processing. However, it omits permissions, idempotency, reversibility, and what a successful write returns, leaving significant behavioral gaps.

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 tight sentences with no filler, front-loading the primary use case before the fallback and safety note. Every sentence carries unique information.

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?

For a three-parameter tool with no output schema and no annotations, the description covers the main mode-selection and safety behavior well. It is still silent on return values and what happens if both raw and candidates are omitted, leaving minor gaps for an agent trying to interpret results.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3. The description adds priority semantics ('PRIMARY' candidates, 'BACKSTOP' raw) that are not in the schema, helping an agent decide which parameter to populate first. The library parameter's detailed usage guidance lives entirely in the schema, not the description.

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

Purpose4/5

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

States a specific verb (ingest) and resource (memory), and distinguishes two operating modes (PRIMARY/BACKSTOP). However, it does not differentiate from sibling tools like mind_add or mind_learn that also write memory, so an agent must infer which to pick.

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 tells when to use candidates vs raw ('PRIMARY: pass candidates... BACKSTOP: omit candidates...'), giving clear context for parameter selection. It stops short of naming alternative sibling tools or when not to use this tool at all.

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

Deploy Server

Other Tools