trustcase-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port to use when running in streamable HTTP mode (e.g., PORT=8787 node dist/index.js). | |
| TRUSTCASE_FEED_URL | No | Point it somewhere else with TRUSTCASE_FEED_URL, which also accepts a local file path. | https://trustcase.dev/api/use-cases.json |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_use_casesA | Search Trustcase, a directory of 97 practical AI agent use cases, each rated with a 0 to 100 trust score. Use this whenever the user asks about AI agent safety, trust or risk for a task, for example 'is it safe to let an agent change my live eBay prices', 'should I let AI reply to customers', 'what can go wrong if an agent does X', 'how do I set up an agent to do Y safely', what an agent should need approval for, or which tools or models to use for an agent task. Pass a few plain words for the task as query (for example 'ebay prices' or 'customer replies'). Returns, for each match: slug, title, category, summary, trust score and a trustcase.dev link. Then call get_use_case with the best slug for what the agent does alone, what waits for human approval and a setup prompt. Read-only. |
| get_use_caseA | Get the full Trustcase entry for one AI agent use case by slug (from search_use_cases). Use it to answer whether a task is safe to hand to an agent, what could go wrong, what needs human approval, and how to set it up. Returns: the 0 to 100 trust score with its breakdown (access, human approval, undo and logs, scope, each with a reason), what the agent does on its own, what waits for a human yes, suggested tools, models and apps it works in, a copyable setup prompt, and the trustcase.dev link. Read-only. |
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 2 tools
The two tools form a clear search-then-detail workflow: search_use_cases returns candidate slugs, and get_use_case retrieves the full entry for one slug. Their descriptions explicitly state this sequence, so an agent should not confuse them.
Both names follow the same snake_case verb_noun pattern: search_use_cases and get_use_case. The resource noun is consistent, making the pair predictable.
Two tools is minimal but appropriate for a read-only directory lookup service with a search/detail split. It is slightly thin compared to richer API surfaces, but no tool appears redundant.
The surface covers the core workflow: find a use case by task description and retrieve its full trust assessment, approval boundaries, setup prompt, and link. Minor gaps exist, such as browsing by category or fetching an entry by slug without first searching, but these are workable.