Borrowing it
Nothing to install: this file belongs to imbenrabi/Financial-Modeling-Prep-MCP-Server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/imbenrabi/Financial-Modeling-Prep-MCP-Server/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/imbenrabi/Financial-Modeling-Prep-MCP-ServerWrote 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.
[](https://agentmods.dev/instructions/imbenrabi/financial-modeling-prep-mcp-server/copilot-instructions)<a href="https://agentmods.dev/instructions/imbenrabi/financial-modeling-prep-mcp-server/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/imbenrabi/financial-modeling-prep-mcp-server/copilot-instructions/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.
<a href="https://agentmods.dev/instructions/imbenrabi/financial-modeling-prep-mcp-server/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/imbenrabi/financial-modeling-prep-mcp-server/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01535 | $0.01535 |
| Opus 5 | $0.00767 | $0.00767 |
| Sonnet 5 | $0.00307 | $0.00307 |
| Haiku 4.5 | $0.00153 | $0.00153 |
Grade C, and why
Financial-Modeling-Prep-MCP-Server copilot-instructions.md scanned grade C with 1 finding 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
Verify clients properly extract API keys from session context vs constructor parameters. Copies of this mod
2 near-identical copies found in the catalogue:
- Financial-Modeling-Prep-MCP-Server copilot-instructions.md — 91% identical, 7 lines differ
- Financial-Modeling-Prep-MCP-Server copilot-instructions.md — 91% identical, 7 lines differ
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Coding Agent Instructions for Financial Modeling Prep MCP Server
Architecture Overview
This is a Model Context Protocol (MCP) server that exposes 253+ financial tools across 24 categories using the Financial Modeling Prep API. The codebase uses a stateful server architecture powered by the Smithery SDK with three operational modes:
- Dynamic Mode: Starts with 3 meta-tools, loads toolsets on-demand via
enable_toolset()calls - Static Mode: Pre-loads specific toolsets at startup via
FMP_TOOL_SETSenvironment variable or CLI arg - Legacy Mode: Loads all 253 tools at startup (default)
Key Components & Data Flow
Core Architecture Pattern
HTTP Request → FmpMcpServer → ClientStorage (by clientId) → McpServerFactory → DynamicToolsetManager → Individual Tool Modules
FmpMcpServer(src/server/FmpMcpServer.ts): Main HTTP server using Smithery SDK's stateful server wrapperClientStorage(src/client-storage/ClientStorage.ts): LRU storage with TTL keyed by clientId (derived from access token)McpServerFactory(src/mcp-server-factory/McpServerFactory.ts): Creates MCP server instances per sessionDynamicToolsetManager(src/dynamic-toolset-manager/DynamicToolsetManager.ts): Runtime tool loading/unloadingServerModeEnforcer(src/server-mode-enforcer/ServerModeEnforcer.ts): Handles config precedence and mode validation- Tool modules (
src/tools/*.ts): Individual tool registration functions following consistent patterns
Client Isolation Pattern
Exactly one McpServer instance and DynamicToolsetManager is maintained per clientId, where clientId = client:<sha256(token)>. If no token is provided, a per-request anon:<uuid> is used (no reuse). The SDK manages sessionId, but caching does not use it.
Development Workflows
Testing Strategy
- Framework: Vitest with comprehensive mocking patterns
- Key Pattern: Mock external dependencies in test files using
vi.mock()at module level - Run Tests:
npm test(watch mode) ornpm run test:run(single run) - Coverage:
npm run test:coverage
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 · 136 lines · 1,535 tokens per session scan C 284388b3c960
Financial-Modeling-Prep-MCP-Server copilot-instructions.md is an instructions file published in the GitHub repository imbenrabi/Financial-Modeling-Prep-MCP-Server (143 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,535 tokens to every session, about $0.0077 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
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.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.