rag-rat

Overview Schema Related Servers Score Discussions

memory_create

Save non-obvious decisions, invariants, and risks as durable memories anchored to a symbol, path, call path, commit, or tracker so the rationale resurfaces for the next agent editing that code.

Instructions

Record a durable, source-anchored repo memory (Invariant / Decision / Risk / BugPattern / …) bound to a symbol, chunk, path, edge/call-path, commit, or tracker ref — so the rationale resurfaces for the next agent editing that code. Capture non-obvious invariants and decisions as you discover them.

Input Schema

TableJSON Schema

Name	Required	Description
`bind`	No	Optional (#463): omit to create an UNANCHORED node (a `Concept` or standalone `Task` that lives only as a graph node). When present, names exactly one code/anchor binding.
`body`	Yes	The memory text (the why + how to apply), max 8000 characters.
`kind`	Yes
`tags`	No
`title`	Yes	One-line summary, max 160 characters.
`source`	No
`payload`	No	Optional structured payload (#465) for a polymorphic node — a `Task`/`Concept`'s kind-specific JSON object (e.g. a task's priority/estimate). Must be a JSON object.
`confidence`	Yes
`created_by`	No

Schema Changelog

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

Addedv0.22.0Aug 2, 2026
Removedv0.21.1Jul 24, 2026

Changed1 schema field changedv0.21.0Jul 24, 2026

addedInput schema / properties / title

Added value: +{
+  "description": "One-line summary, max 160 characters.",
+  "type": "string"
+}

Changed13 schema fields changedv0.18.0Jul 15, 2026
- addedInput schema / $defs / MemoryBindArgs / additionalProperties
```
Added value: +false
```
- removedInput schema / $defs / MemoryBindArgs / properties / github_number
```
Removed value: -{
-  "format": "int64",
-  "type": [
-    "integer",
-    "null"
-  ]
-}
```
- removedInput schema / $defs / MemoryBindArgs / properties / github_owner
```
Removed value: -{
-  "type": [
-    "string",
-    "null"
-  ]
-}
```
- removedInput schema / $defs / MemoryBindArgs / properties / github_repo
```
Removed value: -{
-  "type": [
-    "string",
-    "null"
-  ]
-}
```
- addedInput schema / $defs / MemoryBindArgs / properties / item_key
```
Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
```
- addedInput schema / $defs / MemoryBindArgs / properties / project
```
Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
```
- addedInput schema / $defs / MemoryBindArgs / properties / tracker
```
Added value: +{
+  "description": "Tracker-item binding: all three of `tracker` (e.g. `github`), `project`\n(e.g. `owner/repo`), and `item_key` (e.g. `588`) together.",
+  "type": [
+    "string",
+    "null"
+  ]
+}
```
- removedInput schema / properties / bind / default / github_number
```
Removed value: -null
```
- removedInput schema / properties / bind / default / github_owner
```
Removed value: -null
```
- removedInput schema / properties / bind / default / github_repo
```
Removed value: -null
```
- addedInput schema / properties / bind / default / item_key
```
Added value: +null
```
- addedInput schema / properties / bind / default / project
```
Added value: +null
```
- addedInput schema / properties / bind / default / tracker
```
Added value: +null
```

Changed5 schema fields changedv0.10.1Jul 9, 2026

changedInput schema / $defs / McpMemoryKind / enum

Previous value: -[
-  "Invariant",
-  "Decision",
-  "RejectedAlternative",
-  "Risk",
-  "BugPattern",
-  "TestExpectation",
-  "PerformanceNote",
-  "SecurityNote",
-  "FFIBoundary",
-  "PlatformQuirk",
-  "FollowUp",
-  "OpenQuestion",
-  "Obsolete"
-]New value: +[
+  "Invariant",
+  "Decision",
+  "RejectedAlternative",
+  "Risk",
+  "BugPattern",
+  "TestExpectation",
+  "PerformanceNote",
+  "SecurityNote",
+  "FFIBoundary",
+  "PlatformQuirk",
+  "FollowUp",
+  "OpenQuestion",
+  "Obsolete",
+  "Task",
+  "Concept"
+]

addedInput schema / properties / bind / default

Added value: +{
+  "chunk_id": null,
+  "commit_hash": null,
+  "dir": null,
+  "edge_id": null,
+  "edge_path": null,
+  "edge_sequence_hash": null,
+  "end_id": null,
+  "end_line": null,
+  "github_number": null,
+  "github_owner": null,
+  "github_repo": null,
+  "id": null,
+  "path": null,
+  "path_summary": null,
+  "start_id": null,
+  "start_line": null
+}

addedInput schema / properties / bind / description

Added value: +"Optional (#463): omit to create an UNANCHORED node (a `Concept` or standalone `Task` that\nlives only as a graph node). When present, names exactly one code/anchor binding."

addedInput schema / properties / payload

Added value: +{
+  "default": null,
+  "description": "Optional structured payload (#465) for a polymorphic node — a `Task`/`Concept`'s\nkind-specific JSON object (e.g. a task's priority/estimate). Must be a JSON object."
+}

changedInput schema / required

Previous value: -[
-  "kind",
-  "title",
-  "body",
-  "confidence",
-  "bind"
-]New value: +[
+  "kind",
+  "title",
+  "body",
+  "confidence"
+]

First observedv0.9.0-3b4b4b7Jun 25, 2026

TDQS

A3.5/5.0

Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions 'durable' and 'source-anchored' and says rationale 'resurfaces' later, but it does not state whether creation is idempotent, what response is returned, what side effects occur (e.g., graph changes), or any prerequisites such as index health. This is a significant gap for a create operation.

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?

Two sentences, zero waste. The first sentence front-loads the purpose and scope, and the second is a direct action call. Every phrase earns its place, and the length is appropriate for the complexity.

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

Completeness3/5

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

This is a complex tool with 9 top-level parameters, a nested bind object, and no output schema. The description explains the high-level purpose but omits the return behavior and workflow guidance (e.g., how the memory will be retrievable via memory_search or memory_for_*). The schema carries much of the parameter detail, but the missing usage and output context leaves gaps.

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 only 44%, so the description must compensate. It does add conceptual meaning by mapping kinds (Invariant, Decision, Risk) and binding targets (symbol, chunk, path, call-path, commit, tracker) to the schema. However, it does not clarify other parameters like tags, source, created_by, or payload beyond what the schema already states.

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 uses a specific verb ('Record') with a clear resource ('durable, source-anchored repo memory') and enumerates distinct kinds and binding targets. This clearly differentiates it from siblings like memory_update, memory_search, and memory_for_symbol, which focus on other operations.

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

Usage Guidelines3/5

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

The phrase 'Capture non-obvious invariants and decisions as you discover them' implies the trigger for using this tool (during exploration when you find non-obvious knowledge), but it does not explicitly state when NOT to use it or which sibling tools to prefer for editing/searching. No exclusions or alternatives are named.

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

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/cq27-dev/rag-rat'

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