Repo Context Forge
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_workspacesA | List the local repositories currently available for inspection. Call this before repository-specific tools when the workspace name is unknown. |
| get_repository_treeA | Return a bounded directory and file map for one repository. Use this to understand repository structure before selecting files. Do not use it to retrieve file contents. |
| find_filesA | Find repository files by glob pattern. Use this when filenames, extensions or approximate locations are known. |
| read_fileA | Read a bounded amount of one UTF-8 text file. Large, binary, denied or out-of-workspace files are rejected. |
| read_file_rangeA | Read a specific one-indexed line range from a UTF-8 text file. Prefer this over reading a whole file when the relevant location is already known. |
| get_file_metadataB | Return metadata for one repository file without reading its full contents. |
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 6 tools
Each tool targets a distinct aspect: workspace discovery, structural overview, pattern-based file search, whole-file reading, precise line-range reading, and metadata retrieval. read_file and read_file_range are differentiated by their descriptions, making selection unambiguous.
All tool names follow a consistent verb_noun pattern in snake_case, using clear verbs (list, get, find, read) and specific nouns. This makes the tool set predictable and easy to navigate.
With six tools, the server is well-scoped for a repository context purpose. Each tool occupies a clear niche with no redundancy, and the count is within the ideal range for a focused utility.
The set covers the main workflow: workspace discovery, structure mapping, file search, content reading (whole and partial), and metadata. A content-search (grep-like) tool is a minor gap, but the current surface handles typical repository inspection tasks effectively.