Native Research MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NATIVE_RESEARCH_MODEL | No | Model identifier. Default is deepseek-flash. | |
| NATIVE_RESEARCH_API_KEY | Yes | Provider credential; no file fallback. Set in the environment that starts the server. | |
| NATIVE_RESEARCH_BASE_URL | No | Responses API base URL. Default is https://api.deepseek.com/v1. | |
| NATIVE_RESEARCH_DATA_DIR | No | Local evidence and state directory. When no data directory is set, the server uses the account data directory from platformdirs. | |
| NATIVE_RESEARCH_REQUEST_TIMEOUT | No | Timeout for provider requests. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Start a research task. Continue with its current revision. Reuse evidence before another web request.
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 |
|---|---|
| research_startB | Start a research task with a goal and scope. Domain preferences do not restrict provider browsing. Budgets apply between requests. |
| research_statusA | Read the current revision, request status, and evidence count without a provider request. |
| research_evidenceA | Read saved evidence by ID without a provider request. Evidence contains model extractions, not raw page bytes. |
| deepseek_searchB | Extend the task with native web research. State the missing evidence. Set refresh for new verification instead of a cached result. |
| deepseek_read_urlB | Read a public page for a specific question. A new focus extends earlier evidence. Native tools can truncate long pages. |
| research_recoverC | Recover from saved visible evidence. This operation uses a model request without search or fetch tools. |
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 6 tools
The tools cover distinct research lifecycle stages: start, search, URL read, evidence read, status, and recovery. There is some potential overlap between research_evidence and research_recover, and between deepseek_read_url and research_evidence, but the descriptions clarify saved extraction versus provider fetch versus recovery.
All names use snake_case and coherent domain prefixes: research_* for task lifecycle and deepseek_* for provider actions. The only inconsistency is that some research_* names are verbs (start, recover) while others are resource nouns (evidence, status).
Six tools is well within the 3-15 range and each covers a distinct step in the research workflow. No tool appears redundant or filler.
Core research lifecycle is covered: start, search, read, inspect evidence/status, and recover. Minor gaps remain, such as no explicit finish/synthesize/cancel or list-evidence operation, but agents can work around these via status and evidence IDs.