deeptrue MCP
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_PORT | No | HTTP listen port. | |
| DEEPTRUE_ORG | No | Optional default organization domain/slug. | |
| MCP_BIND_HOST | No | HTTP listen host. | |
| MCP_PUBLIC_URL | No | Public MCP URL used as the OAuth resource indicator. Default `https://mcp.deeptrue.ch`. | https://mcp.deeptrue.ch |
| DEEPTRUE_API_KEY | Yes | deeptrue `dt_…` API key for stdio. Required. | |
| DEEPTRUE_API_BASE | No | API origin. Default `https://api.deeptrue.ch`. | https://api.deeptrue.ch |
| MCP_ALLOWED_HOSTS | No | Comma-separated Host allowlist for HTTP. | |
| DEEPTRUE_OAUTH_ISSUER_URL | No | OAuth issuer URL. Defaults to the API origin. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
DeepTrue research assistant MCP. Typical project sequence: create_project → submit_briefing_answers → accept_project → start_fielding → finish_fielding. Mutating tools require confirm=true and write scopes (mcp:write or a finer write scope). Organization is per request: pass the organization argument or send X-DeepTrue-Org. set_active_organization does not stick on stateless HTTP. Do not invent API fields; prefer get_project / get_survey before updates. Respondent tools redact PII unless include_pii=true and the token has mcp:pii (not granted by mcp:write). Remote OpenAI/ChatGPT connectors must use OAuth bearer tokens; do not configure API keys (dt_…) for ChatGPT.
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 |
|---|---|
| list_organizationsA | List organizations available to the authenticated DeepTrue user. Use when choosing an org context. |
| get_organizationB | Get organization address/info for one organization domain/slug. The choice applies only to this call. |
| set_active_organizationA | Validate that the user can use an organization. Does not persist across stateless HTTP requests. Pass organization on later tools or send X-DeepTrue-Org / DEEPTRUE_ORG. |
| list_projectsB | List DeepTrue projects in the active organization. Use for inventory and status scans. |
| get_projectA | Fetch a single project by numeric id. Use before lifecycle or briefing changes. |
| create_projectA | Create a project in the active organization. Use when starting a new research brief. Requires mcp:write. |
| update_projectB | PATCH project fields (name/json/etc). Use for briefing answer edits before accept. |
| get_briefingB | Read flattened briefing answers JSON for a project. |
| submit_briefing_answersA | PATCH project.json with briefing answers. Use before accept_project. Requires confirm=true. |
| accept_projectA | Accept a project offer and spawn the survey. Sequence: briefing → accept → collect. Requires confirm=true. |
| start_fieldingA | Begin data collection (collect) for an accepted project. Requires confirm=true. |
| finish_fieldingB | Finish a project that is collecting data. Requires confirm=true. |
| archive_projectB | Archive a project. Requires confirm=true. |
| restore_projectA | Restore an archived project. Requires confirm=true. |
| list_surveysC | List surveys in the active organization. |
| get_surveyC | Fetch a survey by uuid. |
| update_survey_structureA | PATCH an existing survey with a documented survey payload only. Requires confirm=true. Do not invent schema fields. |
| get_survey_statisticsC | Fetch survey statistics by project uuid. |
| list_respondentsA | List respondent progress rows for a survey (status, timing, quota, furthest question). PII redacted unless include_pii=true and token has mcp:pii scope. |
| get_feasibilityA | Fetch a provider ops snapshot from the existing admin routes (cint/status, dynata/status, bilendi/projects). These routes return 403 for non-admins. There is no separate member feasibility route. |
| list_panel_projectsA | List Cint demands or audit, Bilendi projects or audit, or Dynata projects or audit. These routes require a deeptrue admin. A 403 is an admin refusal, not an empty list. |
| list_reportsB | List report files for the active organization. |
| get_reportB | Fetch a report file by id. |
| get_report_layoutsC | Read project report layouts for audience admin or org. |
| trigger_report_refreshA | POST project report HTML via projects/{id}/report/. That route is limited to deeptrue admins. Requires confirm=true. A 403 means the account is not an admin; nothing was saved. |
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 25 tools
Most tools target clearly distinct resources and actions, with descriptions that help distinguish project, survey, briefing, fielding, and reporting operations. Minor overlap exists between update_project and submit_briefing_answers, and between get_feasibility and list_panel_projects, but these are still reasonably separable.
Tool names consistently use snake_case with a verb-first pattern such as list_projects, get_survey, create_project, and archive_project. Minor variations like set_active_organization and start_fielding still fit the same readable convention.
The server covers a broad platform spanning organizations, projects, briefings, fielding, surveys, respondents, admin feasibility, and reports, so 25 tools is plausible. However, the surface is heavy and near the threshold where tools become harder to discover and choose among.
Core project lifecycle and briefing-to-fielding workflows are well covered, and surveys and reports have read/update operations. However, notable gaps remain, such as no create/delete survey, no delete project, no respondent detail tool, and no report creation workflow.