jev-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JEV_MCP_MODEL | No | Pin a Jev version, e.g. jev-1.12. | jev-latest |
| TYPESAFE_API_KEY | Yes | Your TypeSafe API key, required to use the Jev model. | |
| TYPESAFE_BASE_URL | No | Custom API endpoint for TypeSafe. |
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 |
|---|---|
| jev_verifyA | Check each claim against provided evidence text with TypeSafe Jev. Returns per claim: verdict (verified | contradicted | unsupported), full probability distribution, confidence, and whether the verdict stands on its own (auto) or needs human review. Pattern: docs.typesafe.ai/cookbooks/citation_check. Pass reports, PR descriptions, or agent briefs as claims and their cited sources, diffs, or documents as evidence. |
| jev_screenA | Judge fetched or external text with TypeSafe Jev before an agent reads it: probability it contains instructions aimed at an AI agent (prompt injection), whether it has substantive content, and (when a purpose is given) whether it is relevant to the task. Returns a recommendation: pass | review | block | skip. Pattern: docs.typesafe.ai/cookbooks/llm_guardrails. |
| jev_findA | Rank candidates against a plain-language query with TypeSafe Jev — no embeddings needed. One Choice scores every candidate id by how well it answers the query, plus a Noul checks whether any candidate addresses the query at all (so a confident 'top hit' cannot masquerade as an answer). Pattern: docs.typesafe.ai/cookbooks/semantic_find. Use for 'which file/note/line covers X' across up to 250 candidates. |
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 clearly distinct purpose: verifying claims against evidence, screening text for prompt injection and relevance, and ranking candidates against a query. There is no meaningful overlap or ambiguity between them.
All tool names follow the same 'jev_' prefix plus a single verb in snake_case: jev_verify, jev_screen, jev_find. The pattern is uniform and predictable.
Three tools is a reasonable, focused scope for this server. Each tool covers a distinct high-level capability and none feel redundant or excessive.
The set covers the main apparent workflows: verification, guardrail screening, and semantic finding. Minor gaps could exist around configuration or explanation, but the core surface feels complete for its focused purpose.