Ollama Web Search MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OLLAMA_API_KEY | Yes | Your Ollama API key from ollama.com. Required to authenticate requests to Ollama Cloud's Web Search and Web Fetch APIs. | |
| OLLAMA_MAX_RETRIES | No | Maximum number of retries for transient failures and rate limits. Must be between 0 and 5. | 2 |
| OLLAMA_TIMEOUT_SECONDS | No | Timeout in seconds for API requests. Must be greater than 0 and up to 300. | 30 |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| web_searchB | Search the public web with Ollama Cloud. Args: query: A concise search query. Do not include secrets or confidential data. max_results: Number of results to return, from 1 to 10. |
| web_fetchB | Fetch and extract the main content of one public HTTP(S) web page. Args: url: Absolute public HTTP or HTTPS URL to fetch. |
| search_and_fetchA | Search the web and fetch the top results in one call. This convenience tool reduces agent round trips. Individual fetch failures are returned beside successful pages instead of failing the whole operation. Args: query: A concise search query. Do not include secrets or confidential data. max_results: Number of search results to return, from 1 to 10. fetch_top: Number of top result pages to fetch, from 1 to max_results. |
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 clear distinct role: web_search retrieves results, web_fetch retrieves page content, and search_and_fetch combines both as an explicit convenience. The overlap of search_and_fetch with the pair is well-explained and does not cause ambiguity.
All names use snake_case and are readable verb_noun or verb_pattern forms. The minor deviation is that web_search and web_fetch share a 'web_' prefix while search_and_fetch does not, but this is not confusing.
Three tools is well-scoped for a web search and fetch server; each tool earns its place by covering a core operation. Adding more would likely introduce redundancy.
The surface covers search, single-page fetch, and combined search+fetch, which are the essential operations for this domain. No obvious lifecycle gaps are apparent for a web search utility.