Anclum
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ANCLUM_DB | No | Path to the SQLite catalogue, opened read-only. For a local checkout, point this at your own copy of the SQLite file (schema: items and ai_tools tables). | /opt/dsh-app/var/aggregator.db |
| SKILLTIDE_DB | No | Legacy alias for ANCLUM_DB; path to the SQLite catalogue, opened read-only. |
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 |
|---|---|
| search_toolsA | Search Anclum's catalogue of 8,250 MCP servers, agent skills and open-source AI projects, plus 1,500 AI tools. Returns name, url, one-line summary and tags. Read-only. |
| get_toolA | Get one catalogue entry by its key (the slug used in its Anclum URL). Returns the full record: name, url, description, tags, source, first/last seen. Read-only. |
| list_categoriesA | List the catalogue's taxonomies: AI-tool categories (with counts) and field tags (e.g. "MCP 服务", "Agent 技能"). Useful for then calling search_tools with a category. Read-only. |
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 has a clearly distinct role: search_tools searches catalogue entries, get_tool retrieves a single entry by key, and list_categories lists taxonomy metadata. There is little risk of confusing these operations.
All three tools follow a consistent snake_case verb_noun pattern: search_tools, get_tool, list_categories. The convention is predictable and easy to parse.
Three tools are well-scoped for a read-only catalogue lookup server: one for discovery, one for detail retrieval, and one for taxonomy browsing. Each tool earns its place without unnecessary surface area.
The surface covers search, detail retrieval, and category/tag discovery for a read-only catalogue, which is the core workflow. Minor gaps such as explicit pagination or bulk listing by source are not fatal because search_tools can likely approximate them.