mcp-web-calc
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MAX_BYTES | No | Maximum download limit in bytes for the fetch_url tool (e.g., 20MB). | 20971520 |
| USER_AGENT | No | User agent string for network requests. | mcp-web-calc/0.3 (https://local) |
| MAX_RESULTS | No | Default number of results for the search_web tool. | 10 |
| HTTP_TIMEOUT | No | Timeout in milliseconds for all network requests. | 15000 |
| LANG_DEFAULT | No | Default language code. | vi |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_webA | Two-tier web search: runs fast DuckDuckGo HTML search by default, escalates to Puppeteer/Bing if results are insufficient. No API keys required. |
| fetch_urlA | Fetches content from a URL (HTML/PDF) and extracts readable text. Supports truncation modes: compact (~3000 chars), standard (~8000 chars, default), full (no truncation). Output formats: markdown (default), text, html. |
| summarize_urlC | Fetches content from a URL and generates a concise summary. |
| wiki_getB | Retrieves a Wikipedia summary for a given title. Supports multiple languages (default: en). |
| wiki_multiB | Retrieves Wikipedia summaries in multiple languages for a given term. Uses langlinks to map titles accurately across languages. |
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
Most tools have distinct purposes: fetch_url extracts content, search_web performs web searches, summarize_url summarizes content, and wiki_get/wiki_multi retrieve Wikipedia data. However, fetch_url and summarize_url both fetch content from URLs, which could cause minor confusion about when to use each, though their outputs differ (raw content vs. summary).
All tool names follow a consistent snake_case pattern with clear verb_noun structures: fetch_url, search_web, summarize_url, wiki_get, and wiki_multi. This predictability makes it easy for agents to understand and select tools without naming confusion.
With 5 tools, this server is well-scoped for its web calculation and information retrieval purpose. Each tool serves a specific function (e.g., fetching, searching, summarizing, Wikipedia access), and none appear redundant or excessive, fitting typical expectations for such a domain.
The tool set covers key web-based operations: content fetching, web searching, summarization, and Wikipedia access. Minor gaps exist, such as no explicit tools for updating or deleting data, but this is reasonable given the server's focus on retrieval and analysis. Agents can likely work around this with the provided tools.