seekpeek
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEEPSEEK_API_KEY | Yes | Required. Your DeepSeek API key | |
| SEEKPEEK_TIMEOUT | No | Per-request timeout in seconds | 60 |
| DEEPSEEK_BASE_URL | No | API base URL (proxy or gateway) | https://api.deepseek.com |
| SEEKPEEK_FETCH_QPS | No | Client-side fetch rate limit | 5 |
| SEEKPEEK_SEARCH_QPS | No | Client-side search rate limit | 5 |
| SEEKPEEK_MAX_RETRIES | No | Retries on 408 / 429 / 5xx | 2 |
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 |
|---|---|
| searchA | Search the live web (DeepSeek Search API) and get ranked, structured results. Each result carries a rerank score (0-3; >=1.5 is high-quality), site authority (0-4; >=3 is highly
authoritative), publication date, a short snippet and a long model-oriented summary. Set
Use it for anything after your training cutoff, current events, versions, prices or APIs. |
| fetchA | Fetch one web page (DeepSeek Fetch API) and return its title plus the full text as Markdown. Use it on a |
| fetch_manyA | Fetch up to 10 web pages in one call and return each as Markdown. Fetches run concurrently under the account rate limit, and one failing URL never fails the call — the
error is reported in place. Prefer this over several |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| web-research | Turn a topic into a research brief that uses seekpeek's search operators well. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| search-syntax | Search operators, rerank/authority thresholds and result field meanings. |
TDQS
Scored across 3 tools
search (discovery), fetch (single page), and fetch_many (batch page) target clearly separable operations. The only potential overlap—fetch vs fetch_many—is explicitly resolved in the description, which tells the agent to prefer fetch_many when URLs are already known. No realistic misselection risk.
All names are lowercase snake_case verbs, and fetch_many follows the same verb as fetch with a transparent bulk suffix. The pattern is fully predictable across the set.
Three tools is well-scoped for a web search-and-retrieve server: one discovery tool, one single-item retrieval, one batch retrieval. Each tool earns its place with no redundancy or filler.
search + fetch + fetch_many covers the core retrieval lifecycle, including batch retrieval, error handling per URL, and rich result metadata. Minor gaps remain, such as no documented pagination/offset for search or structured extraction beyond Markdown.