LLMMcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NO_PROXY | No | Comma-separated proxy bypass list. | |
| ALL_PROXY | No | Standard all-protocol proxy environment variable. | |
| HTTP_PROXY | No | Standard HTTP proxy environment variable. | |
| LLMMCP_TLS | No | TLS trust mode: truststore, certifi or off. | truststore |
| HTTPS_PROXY | No | Standard HTTPS proxy environment variable. | |
| LLMMCP_PROXY | No | Explicit proxy URL. Overrides all other proxy sources. | |
| LLMMCP_CONFIG | No | Path to the LLMMCP config file. Defaults to ~/.llmmcp/config.json when unset. | |
| LLMMCP_BROWSER | No | Chrome or Edge executable used for headless DOM rendering. Auto-detected when unset. | |
| LLMMCP_ENGINES | No | Fallback engine order for engine=auto. | google,bing,gnews |
| LLMMCP_TIMEOUT | No | Default request timeout in seconds. | 30 |
| LLMMCP_LOG_LEVEL | No | Logging verbosity. | INFO |
| LLMMCP_MAX_BYTES | No | Response body size cap in bytes. | 5000000 |
| LLMMCP_GOOGLE_HOST | No | Google host used for search. | www.google.com |
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| web_searchB | Search the web. Returns a numbered list of results (title, URL, snippet) plus structured results. engine='auto' walks the configured fallback chain. |
| web_fetchB | Fetch a URL and return its readable content. format is markdown (default), text or html; JSON is pretty printed; binaries are rejected. |
| web_diagnoseA | Diagnose the local setup: resolved proxy (credentials redacted), TLS mode, browser availability, search engines and an optional live connectivity probe. |
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 targets a distinct operation: web_search retrieves results, web_fetch retrieves content from a URL, and web_diagnose inspects local configuration. There is no overlap in purpose or expected inputs, making selection unambiguous.
All three tools follow the same predictable pattern: a 'web_' prefix plus a clear verb (search, fetch, diagnose). The convention is consistent and self-explanatory.
Three tools is a focused, well-scoped set for a web access server, and each tool has a clear role. It is slightly on the lean side relative to the 3-15 typical range, but nothing feels superfluous or missing at this scale.
The core lifecycle for web access is covered: searching, fetching results, and diagnosing the environment. Minor gaps exist, such as no batch-fetch or multi-URL operations, but these are workarounds rather than blockers.