What is fiss-mcp CLAUDE.md?

A read-only MCP server that connects Claude Code to Terra.Bio workspaces through the FISS API. Terra.Bio is a platform for running and monitoring scientific data workflows, and WDL is a language for describing those workflows.

Use it to develop and debug WDL pipelines, monitor Terra workflow runs, inspect logs, interpret failures, and run regression tests against benchmark data.

It lets an agent inspect workflow projects and diagnose runs without accidentally changing workspaces or launching jobs.

How broadinstitute/fiss-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to broadinstitute/fiss-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/broadinstitute/fiss-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/broadinstitute/fiss-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/broadinstitute/fiss-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/broadinstitute/fiss-mcp/claude-md)

Your own site

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

Per session 5,470 This file is loaded in full into every session.

When invoked 5,470 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	$0.05470	$0.05470
Opus 5	$0.02735	$0.02735
Sonnet 5	$0.01094	$0.01094
Haiku 4.5	$0.00547	$0.00547

Measured 5d ago against content hash 681b547a6018, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

fiss-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 5d 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 · 428 lines

How it starts

The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Terra.Bio MCP Server

Project Purpose

Build an MCP (Model Context Protocol) server that enables Claude and Claude Code to interact with Terra.Bio workspaces via the FISS (firecloud) API. Primary use cases:

Develop and debug WDL pipelines with Claude Code monitoring Terra workflow runs
Run regression tests against benchmark datasets on Terra
Monitor job submissions, interpret logs, and debug failures

Technical Approach

Framework: Python with FastMCP (mcp Python SDK)
API Client: firecloud/FISS Python library
Authentication: Local user has pre-authenticated Google credentials that work with FISS
Development Guide: Follow MCP Specification and FastMCP docs

Key Design Decisions

Read-Only Safety Mode

Default Behavior: Server runs in read-only mode to prevent accidental modifications to Terra workspaces
Protected Operations: Write operations are disabled by default:
- update_method_config - Updating workflow configurations
- copy_method_config - Copying workflow configurations
- submit_workflow - Launching new workflows
- abort_submission - Canceling running workflows
- upload_entities - Upserting entity data (creates or updates rows)
Enabling Writes: Use --allow-writes command-line flag to enable write operations
Error Messages: Clear, actionable messages guide users to restart with --allow-writes if needed
Testing: Comprehensive test coverage with enable_writes pytest fixture for write tool tests

Usage Examples:

# Default: Read-only mode (safe for exploration)
python -m terra_mcp.server

# Enable write operations (for active development)
python -m terra_mcp.server --allow-writes

Workspace Identification

Always require explicit workspace namespace + name in tool calls
No implicit "current workspace" to avoid confusion
Format: workspace_namespace="my-namespace", workspace_name="my-workspace"

Read the full file on GitHub · 428 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.

5d ago Changed · +13 lines · +240 tokens per session 681b547a6018
9d ago First seen · 415 lines · 5,230 tokens per session scan A 3127b6ce993f

Subscribe to this mod's changes

fiss-mcp CLAUDE.md is an instructions file published in the GitHub repository broadinstitute/fiss-mcp (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 5,470 tokens to every session, about $0.0273 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.

Scientific

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

fiss-mcp: Instructions file for Claude Code