specir-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SPEC_IR_DB | Yes | Path to the SQLite database file containing SpecIR data |
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
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| specir_resolveC | Resolve an exact domain entity, section, table, or figure. |
| specir_fetchB | Fetch an entity by canonical UID, optionally with graph edges. |
| specir_explainD | Combine a named entity with its defining section. |
| specir_searchC | Search structured entities or raw passages. |
| specir_statusB | Report plugin state and database coverage. |
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 5 tools
Each tool has a distinct primary purpose: resolve by name, fetch by UID, explain with context, search broadly, and status for system info. Resolve and fetch are similar but differentiated by input type (name vs UID), while explain is a composite of entity and section.
All tools follow a consistent specir_ prefix followed by a clear action verb (resolve, fetch, explain, search, status). The pattern is uniform and predictable, making it easy to infer tool behavior from name alone.
Five tools is ideal for a focused specification entity retrieval service. Each tool covers a distinct interaction mode without redundancy, and the count is well within the typical range for a useful MCP server.
The tool set covers the core needs for querying a spec database: search, targeted retrieval by name or UID, contextual explanation, and system status. No obvious lifecycle operations are missing because the domain is read-only retrieval, and the provided methods form a complete workflow.