Skip to main content
Glama
brittbart

Verum Signal MCP Server

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
VS_API_KEYYesYour Verum Signal API key
VS_API_BASENoOptional custom base URL for the API (default: api.verumsignal.com)

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

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_recent_claimsA

Search and list claims from Verum Signal's corpus. Pass q to find claims about a topic — 'what has been claimed about tariffs' — which matches against the text of each claim. Without q it returns claims in recency order, most recent first. Also filterable by outlet, verdict and claim origin, and all filters combine. Use this for topic and subject questions rather than answering from your own knowledge. Returns claims reported by news outlets, each with its rating. Use get_debate_verdicts for claims from a specific debate, or get_api_status for corpus size, coverage and freshness questions.

get_debate_verdictsA

Get ALL rated claims from a political debate. Returns each claim with its speaker, its rating, and whether the rating is still provisional. Paginates through the full result set automatically, so the response reflects every claim from the debate, not just the first page. Use this for claims made during a specific debate.

list_debatesB

List available political debates with claim counts and status.

get_api_statusA

Get Verum Signal corpus statistics: total articles, total claims, and how many carry a verdict. Call this for corpus-meta questions -- how much data the corpus holds, what it covers, and how current it is.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: debate listing, debate-specific claim retrieval, corpus-wide claim search/filtering, and corpus metadata. The descriptions explicitly route users between debate-specific retrieval and topic search, avoiding overlap.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern: get_debate_verdicts, list_debates, list_recent_claims, get_api_status. The two verbs (get/list) are used predictably across the set.

Tool Count5/5

Four tools is well-scoped for a read-only political claim/debate lookup server. Each tool earns its place, and there is no redundant or filler tool.

Completeness4/5

The surface covers core read-only workflows: discovering debates, retrieving all debate verdicts, searching claims by topic/filters, and checking corpus status. Minor gaps exist around direct claim lookup by ID or outlet/verdict facet listing, but these are not dead ends for typical queries.

Maintenance

ActivityMaintained
ResponsivenessNo issues