fluencydrift-mcp
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_architectural_recordsA | List the fluencyloop-tracked repo's resolved architectural records (concepts, principles, decisions). |
| check_driftA | Compare the repo's recorded architecture against reality and report structured drift findings. |
| explain_recordA | Explain one architectural record by name. |
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 3 tools
Each tool serves a distinct function: listing all records, checking drift, and explaining a specific record. No overlapping purposes, so an agent can easily select the right tool.
All tool names follow a consistent verb_noun pattern with underscores: list_architectural_records, check_drift, explain_record. This is uniform and predictable.
Three tools is a well-scoped size for a focused drift-checking utility. Each tool is essential and there is no bloat or sense of missing critical functionality.
For its stated purpose of monitoring architectural drift, the set covers the full workflow: list records to see what exists, explain a record to understand it, and check drift to identify mismatches from reality. No apparent gaps or dead ends.