bleurs
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 |
|---|---|
| surfaceA | Get the exact API of a Python module, class, or project file: every public name with its real signature and a one-line summary. Reads the installed package or parses the project file, so the answer is always current. Use this INSTEAD OF reading a file when you need to know how to call something. It is typically 5-10x fewer tokens than the source and contains everything needed to make a correct call. Cheap enough to re-ask at any time rather than holding it in context. |
| contextA | Get everything you need to edit a file correctly, in one budgeted block: the file's own API plus the exact surface of every module it imports, followed transitively through project code. Call this INSTEAD OF reading a file and its dependencies, before you start editing. It is a dependency closure computed from the code — not a similarity search — so it contains what the file actually uses, and it is typically several times cheaper than reading the same files. Ask again whenever you need it rather than holding it in context. |
| verifyA | Check Python source for references that provably do not exist -- invented packages, invented methods on real libraries, helpers missing from this project. Returns the blocked references and the real API of whatever each one got wrong. Run this on code you are about to write. It only reports what it can prove absent, so a clean result is meaningful and a block is never a guess. |
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
The tools have distinct purposes: surface provides API signatures, context expands to include dependency closure, and verify checks for invalid references. There is slight overlap between surface and context (both return APIs), but descriptions make the difference clear.
All names are single lowercase verbs (surface, context, verify), which is a consistent style, but they do not follow a more informative verb_noun pattern. The naming is predictable in form but somewhat vague in conveying domain.
Three tools is at the lower end of the ideal range but each tool is substantial and covers a distinct need. The count feels appropriate for a focused Python code intelligence server.
The domain of Python code analysis is well covered: surface for understanding API, context for editing with dependencies, and verify for validating references before writing. Minor gaps exist (e.g., no explicit search or exploration tool), but they are not critical for the stated purpose.