tero-mcp-lite
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TERO_TOKENS | No | A whitespace/comma-separated list of token:scope pairs, e.g. 's3cr3t:read other:refresh'. Required for authentication. | |
| TERO_INDEX_PATH | No | Path to the Tero index.json file. Defaults to 'docs/tero-index/index.json'. | |
| TERO_TOKENS_FILE | No | Path to a file containing the same token:scope grammar as TERO_TOKENS. Alternative to TERO_TOKENS. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| identifyB | Server identity, version, and whether the Layer-2 gate is open. |
| query_by_idA | Exact lookup by corpus id (RFC-0034, M-1015, DN-87, an issue id). |
| query_by_statusB | All rows with a given status (Accepted, todo, done, …). |
| query_by_kindB | All rows of a given kind (rfc, adr, note, issue, section, …). |
| cross_refA | Breadth-first walk of depends_on/doc_refs edges from a start id/anchor. |
| text_searchB | Ranked free-text search over id/title/summary. |
| citeD | Citations only for a query (kind + its args, as query_*). |
| explainC | EXPLAIN trace only for a query (kind + its args, as query_*). |
| refreshA | Reload the served index from disk (requires the |
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 9 tools
Each tool serves a distinct purpose: querying by status, kind, or ID; full-text search; graph traversal; citation retrieval; query analysis; index refresh; and server identity. No two tools overlap in function, making selection unambiguous.
Naming follows a mix of patterns: three tools use 'query_by_*', while others use bare verbs (cite, explain, refresh, identify) or compound nouns (cross_ref, text_search). The snake_case convention is consistent, but the verb/noun order varies.
With 9 tools, the server is well-scoped for a query-focused corpus service. Each tool earns its place, covering search, lookup, analysis, and maintenance without unnecessary bulk.
Core corpus operations are covered: retrieval by ID, status, kind, text search, and dependency traversal. Minor gaps exist, such as a dedicated tool to list all statuses or kinds, but the existing tools allow agents to work around this.