Schema | tif-score-mcp

tif-score-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`TIF_MODEL`	No	The Claude model to use for scoring and diagnosis	claude-sonnet-4-6
`ANTHROPIC_API_KEY`	Yes	Your Anthropic API key used for making Claude API calls

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": true }

Functions exposed to the LLM to take actions

Name	Description
score_conversationA	Analyze a call transcript and extract structured business intelligence: intent, sentiment, urgency, objections, outcome, topics, missed-opportunity/follow-up flags, revenue signal, churn risk, and a plain-English summary.
get_lead_scoreA	Score a call transcript 0-100 and classify it hot/warm/cold. Internally runs the same analysis as score_conversation, then applies a point-based weighting to the resulting signals.
diagnose_workflow_errorA	Stateless diagnosis of an n8n workflow error: given the workflow JSON and error message, returns a root cause, a minimal proposed fix (or an honest 'not fixable by a workflow edit'), and a confidence level. Does not verify, deploy, or fetch anything live — pair with human or separate review before applying fixedWorkflow.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/dsvxmedia/tif-score-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server