Use it when working on this repository’s HTTP server, client storage, session creation, dynamic toolsets, and financial-data tool modules.

It documents the project’s architecture and development workflow, reducing uncertainty when changing client sessions or tool loading.

Financial-Modeling-Prep-MCP-Server copilot-instructions.md

Q: What is Financial-Modeling-Prep-MCP-Server copilot-instructions.md?

A Copilot instruction file for another Financial Modeling Prep MCP server repository. It describes a server that exposes financial-data tools through MCP, with dynamic, selected, and full tool-loading modes.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/cfocoder/financial-modeling-prep-mcp-server/copilot-instructions

Clone the repo

git clone --depth 1 https://github.com/cfocoder/Financial-Modeling-Prep-MCP-Server

Made for: GitHub Copilot.

Per session 1,431 This file is loaded in full into every session.

When invoked 1,431 The same file — it is already loaded in full.

Security scan C 1 finding. Scan, not verified.

Origin 91% copy Near-identical to another mod 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	$0.01431	$0.01431
Opus 5	$0.00715	$0.00715
Sonnet 5	$0.00286	$0.00286
Haiku 4.5	$0.00143	$0.00143

Measured 2d ago against content hash f5fc6e7a7bf4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

Origin

This is a copy

91% identical to Financial-Modeling-Prep-MCP-Server copilot-instructions.md — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.github/copilot-instructions.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 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_SETS environment 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 wrapper
ClientStorage (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 session
DynamicToolsetManager (src/dynamic-toolset-manager/DynamicToolsetManager.ts): Runtime tool loading/unloading
ServerModeEnforcer (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) or npm run test:run (single run)
Coverage: npm run test:coverage

Read the full file on GitHub · 129 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.

2d ago First seen · 129 lines · 1,431 tokens per session scan C f5fc6e7a7bf4

Subscribe to this mod's changes

Financial-Modeling-Prep-MCP-Server copilot-instructions.md is an instructions file published in the GitHub repository cfocoder/Financial-Modeling-Prep-MCP-Server (0 stars, last pushed 1y ago), licensed Apache-2.0. It adds 1,431 tokens to every session, about $0.0072 per session on Opus 5. A static security scan graded it C with 1 finding (harvests environment variables). It is 91% identical to Financial-Modeling-Prep-MCP-Server copilot-instructions.md, differing in 7 lines, and is treated as a copy.

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