What is tif-score-mcp CLAUDE.md?

A set of instructions for working on tif-score-mcp, a small server with three tools. It analyzes call transcripts, scores potential leads, and diagnoses errors in n8n workflow files; n8n is a tool for connecting automated steps.

It is for helping an agent safely modify, run, and test this specific Node.js project without adding unsupported tools or services.

It gives coding-agent sessions the project's scope, setup details, testing guidance, and an important implementation warning.

How dsvxmedia/tif-score-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dsvxmedia/tif-score-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dsvxmedia/tif-score-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/dsvxmedia/tif-score-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dsvxmedia/tif-score-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/dsvxmedia/tif-score-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/dsvxmedia/tif-score-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dsvxmedia/tif-score-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dsvxmedia/tif-score-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dsvxmedia/tif-score-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 768 This file is loaded in full into every session.

When invoked 768 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00768	$0.00768
Opus 5	$0.00384	$0.00384
Sonnet 5	$0.00154	$0.00154
Haiku 4.5	$0.00077	$0.00077

Measured 9d ago against content hash 2d230f24c721, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

tif-score-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Instructions for any Claude Code session working in this repo.

What this project is

A standalone MCP (Model Context Protocol) server exposing exactly three tools:

score_conversation — analyzes a call transcript and returns structured business intelligence (intent, sentiment, urgency, objections, outcome, etc.).
get_lead_score — scores a transcript 0-100 and classifies it hot/warm/cold, reusing score_conversation's analysis internally.
diagnose_workflow_error — given an n8n workflow JSON and an error message, returns a root cause and a proposed minimal fix (stateless, single-call diagnosis only).

That's the whole scope. Do not add a fourth tool, a database, a web UI, or an HTTP API layer without an explicit new request — this is deliberately a small, focused server.

Tech stack

Node.js, ESM ("type": "module").
@modelcontextprotocol/sdk — stdio transport, McpServer + server.registerTool(name, config, handler). Use registerTool, not the deprecated tool().
zod (v4) for input schemas — pass raw shapes (plain objects of Zod types) to registerTool's inputSchema, not z.object(...)-wrapped schemas.
@anthropic-ai/sdk for all Claude API calls, through the shared src/lib/anthropic.js helper.

Run and test

npm run start — runs the server directly (stdio, expects an MCP client on the other end, not meant to be run standalone in a terminal for output).
npm run test:unit — pure scoring-math tests, no network, no API key needed.
npm run test:client — spawns the real server and calls all three tools over real stdio JSON-RPC. Requires ANTHROPIC_API_KEY in the environment. This makes real, billed API calls.
npx @modelcontextprotocol/inspector node src/index.js — interactive manual testing UI for all three tools.

A gotcha worth knowing

temperature: 0 (used everywhere here for deterministic output) is only accepted by claude-sonnet-4-6 and earlier models. Newer models (Opus 4.7+, Fable 5) reject the temperature param outright with a 400 error. If you ever change TIF_MODEL to a newer model, you must also remove temperature from the callClaude() calls in src/lib/anthropic.js, or every call will fail.

Read the full file on GitHub · 40 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 40 lines · 768 tokens per session scan A 2d230f24c721

Subscribe to this mod's changes

tif-score-mcp CLAUDE.md is an instructions file published in the GitHub repository dsvxmedia/tif-score-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 768 tokens to every session, about $0.0038 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

tif-score-mcp: Instructions file for Claude Code