failure-memory
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| remember_failureB | Qualify and, only when warranted, record one failure with its root cause, repair, deduplication review, and proposed lesson in a single call. |
| recall_failure_lessonsA | Recall up to three lessons from global personal memory using exact, lexical, semantic, or hybrid retrieval and append a privacy-preserving trace. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one records a failure, the other retrieves lessons. No overlap or ambiguity.
Both tools follow a consistent verb_noun pattern: remember_failure and recall_failure_lessons. The naming is predictable and clear.
The server has two tools, which is a bit thin but appropriate for a narrow domain of failure memory. Both tools are essential for the core workflow.
The server covers the primary actions: remembering a failure and recalling lessons. Missing update/delete operations, but these are not essential for the stated purpose of capturing and retrieving lessons. Minor gap.