preact-mcp
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 |
|---|---|
| query_preact_docsB | Query Preact documentation from multiple repositories. |
| get_preact_readmeB | Get the README content from a specific Preact repository |
| list_preact_repositoriesA | List all available Preact repositories that can be queried, this allows you to have information about the Preact ecosystem. |
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 three tools have mostly distinct purposes: listing repositories, querying docs, and fetching a README. However, query_preact_docs and get_preact_readme could overlap conceptually since a README is documentation, creating minor ambiguity about which to use for repo-specific content.
All tool names follow a consistent verb_noun pattern with the same preact prefix: query_preact_docs, get_preact_readme, and list_preact_repositories. The convention is predictable and easy to parse.
With only 3 tools, the set is well-scoped for a focused Preact documentation server. Each tool earns its place by covering discovery, querying, and README retrieval without unnecessary extras.
The surface covers the core documentation workflow: list available repositories, query docs across them, and fetch a repository README. Minor gaps remain, such as fetching a specific document by path or listing files within a repository, but agents can likely work around these via the query tool.