mgi-mind

Official

Overview Schema Source Related Servers Discussions Admin

mind_block

Manage pinned core-memory blocks that are always injected at session start, so agents can set, get, list, or remove stable facts without retrieval.

Instructions

Pinned core-memory blocks (persona / user / current-project): a few small, named notes that are ALWAYS injected at the top of the session context, not ranked retrieval. Use for stable, always-relevant facts the agent must not have to search for. action=set overwrites, get/list read, remove deletes. Content is capped (4KB/block, 32 blocks); this is core memory, not a second store: put searchable knowledge in mind_add instead.

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": {
      "action": "<action>"
    },
    "name": "mind_block"
  }
}

Input Schema

Name	Required	Description
`name`	No	Block name [a-z0-9_-]; required for set/get/remove
`action`	Yes	Operation (default: list)
`content`	No	Block content; required for action=set

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 20, 2026

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses the injection behavior, per-action semantics (set overwrites, get/list read, remove deletes), and hard resource limits (4KB/block, 32 blocks). It does not state what happens on overwrite of a missing block or whether remove is recoverable, which is the remaining gap for a mutation 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?

Front-loads what the tool is and the ALWAYS-injected constraint, then actions, then limits, then the sibling alternative. Dense but every clause adds an operational fact; only the parenthetical example list is mildly expendable.

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 3-param mutation tool with no annotations and no output schema, the description covers purpose, action semantics, capacity limits, and alternatives. Only edge-case behavior (overwrite of a nonexistent block, reversibility of remove) remains undocumented.

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 coverage is 100% with a documented enum, so the baseline is 3, but the description adds semantics the schema lacks — that 'set' overwrites existing content and that 'list' needs no name — plus the storage cap that bounds what content may be passed.

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?

Names the specific resource (pinned core-memory blocks: persona/user/current-project) and its defining behavior (ALWAYS injected at top of session context, not ranked retrieval). This distinguishes it clearly from retrieval siblings like mind_search and mind_recall.

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?

Explicit when-to-use ('stable, always-relevant facts the agent must not have to search for') paired with an explicit when-not and named alternative ('put searchable knowledge in mind_add instead'). No inference required to route between the two tools.

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