learning-loop-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LEARNING_LOOP_MCP_DB | No | Explicit path to the SQLite index database. Defaults to $XDG_DATA_HOME/learning-loop-mcp/index.db. | |
| LEARNING_LOOP_PROJECTS_ROOT | No | Root directory containing project repositories. The server resolves project docs under <PROJECTS_ROOT>/<project>/docs/. | ~/Proyectos |
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": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| searchB | Searches lessons (hybrid FTS5 + KNN) and returns JSON results with a
cite |
| learning_contextC | Returns a legacy lesson list or an explicit cross-source v2 package. |
| capture_outcomeA | Validates and stores a task-local outcome draft without promotion. |
| amnesia_checkC | Runs the deterministic, read-only ADD continuity check. |
| amnesia_evaluateC | Collects structural evidence and validates an explicit Amnesia Test report. |
| project_preflightC | Checks the read-only project start contract before implementation. |
| learning_statusB | Learning-loop status of the project (metrics + validation findings).
Same dict as |
| indexC | (Re)indexes the project into the local index. JSON with the number of
lessons indexed. |
| register_solutionA | Registers (append-only) a verified solution of the project. Forward-only states: observed, fixed-locally, externally-verified,
documented, indexed. JSON with the created revision, or |
| reindex_solutionsC | Rebuilds the |
| solutionsC | Trace (append-only) of the project's solutions ledger. JSON with the list of events ordered by revision. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| learning-loop://format/lessons-format.md | Kit file: lessons-format.md |
| learning-loop://templates/AGENTS-ritual.md | Kit file: AGENTS-ritual.md |
| learning-loop://templates/lessons.md | Kit file: lessons.md |
| learning-loop://templates/errors.yaml | Kit file: errors.yaml |
| learning-loop://templates/solutions.yaml | Kit file: solutions.yaml |
| learning-loop://skills/project-workflow-tdd-kanban/SKILL.md | Kit file: SKILL.md |
| learning-loop://references/hermes-kanban-bootstrap.md | Kit file: hermes-kanban-bootstrap.md |
| learning-loop://templates/decision-checkpoint.md | Kit file: decision-checkpoint.md |
TDQS
Scored across 11 tools
Most tools have distinct purposes, but several pairs overlap in surface intent: amnesia_check vs amnesia_evaluate both concern continuity/Amnesia validation, and learning_context vs search both return lesson-related content. The descriptions help a careful agent differentiate them, but the boundaries are not immediately obvious.
All names use snake_case and are readable, but the pattern is mixed: some are verb_noun (capture_outcome, register_solution, reindex_solutions), some are noun phrases (learning_status, learning_context, project_preflight), and some are bare words (index, search, solutions). This is not chaotic, but it lacks a consistent convention.
Eleven tools is well within the ideal range for a domain-specific server. Each tool serves a distinct role in the learning-loop lifecycle, and none feel redundant or purely decorative.
The toolset covers the main learning-loop workflow: preflight, outcome capture, Amnesia validation, indexing, solution registration, status, and retrieval. Minor gaps exist—such as no explicit promotion tool or lesson deletion—but these may be intentional given the append-only and forward-only design.