What is wrds_mcp CLAUDE.md?

A set of project instructions for wrds-mcp, a service that provides natural-language access to WRDS financial databases for credit and stock analysis. It documents how to run, test, install, and structure the service.

Use it when developing or maintaining wrds-mcp, including its database connection, financial-data tools, guarded SQL queries, and catalog features.

It gives coding agents the project’s commands, architecture, database layers, and safety rules in one place.

How marianosalinas/wrds_mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to marianosalinas/wrds_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/marianosalinas/wrds_mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/marianosalinas/wrds_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/marianosalinas/wrds_mcp/claude-md/github.svg)](https://agentmods.dev/instructions/marianosalinas/wrds_mcp/claude-md)

Your own site

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

Per session 2,452 This file is loaded in full into every session.

When invoked 2,452 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	$0.02452	$0.02452
Opus 5.5	$0.00981	$0.00981
Sonnet 5.5	$0.00490	$0.00490
Haiku 4.5	$0.00245	$0.00245

Measured 2mo ago against content hash a083c3eabb1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wrds_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 2mo 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 · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wrds-mcp

MCP server providing Claude Code with natural language access to WRDS financial data for credit and equity analysis.

Quick Reference

Run tests: python -m pytest tests/ -v
Run server: wrds-mcp or fastmcp run src/wrds_mcp/server.py:mcp
Install dev: pip install -e ".[dev]"

Architecture

Three-tier design: curated tools handle domain-specific logic, query_wrds provides guarded SQL access for ad-hoc analysis, and catalog tools enable schema discovery.

src/wrds_mcp/
├── server.py             # FastMCP entry point, mounts 9 sub-servers
├── db/connection.py      # Singleton WRDS connection with retry (3 attempts, exponential backoff)
└── tools/
    ├── _validation.py    # Input validation + DataFrame-to-JSON conversion
    ├── _schema_docs.py   # Static column documentation (~95 WRDS mnemonics)
    ├── catalog.py        # Tier 3: discovery — live catalog, schema introspection, ID resolution (3 tools)
    ├── query.py          # Tier 2: guarded SQL — read-only SELECT with safety validation (1 tool)
    ├── equity.py         # Tier 1: CRSP stock tools — price history, returns, summary (3 tools)
    ├── bonds.py          # Tier 1: TRACE/FISD/bondret — transactions, prices, returns, covenants (6 tools)
    ├── ratings.py        # Tier 1: Credit ratings from bondret + Compustat fallback (2 tools)
    ├── financials.py     # Tier 1: Compustat leverage/coverage/liquidity + composites (6 tools)
    ├── loans.py          # Tier 1: DealScan syndicated loan terms + covenants (2 tools)
    ├── screening.py      # Tier 1: Issuer/bond screening, benchmarks, relative value (4 tools)
    └── comps.py          # Tier 1: Side-by-side comps table (1 tool)

Three Tiers

Tier 1 — Curated Tools (25 tools): Pre-built tools with domain logic (auto-routing, TTM calculations, multi-source resolution). Use these first.
Tier 2 — query_wrds (1 tool): Guarded SQL escape hatch for any metric not covered by Tier 1. SELECT-only, schema-allowlisted, 10K row limit, 30s timeout.
Tier 3 — Discovery (3 tools): get_data_catalog (what data exists), get_table_schema (column metadata + docs), resolve_identifier (ticker → gvkey/permno/issuer_id).

Read the full file on GitHub · 138 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.

2mo ago First seen · 138 lines · 2,452 tokens per session scan A a083c3eabb1c

Subscribe to this mod's changes

wrds_mcp CLAUDE.md is an instructions file published in the GitHub repository marianosalinas/wrds_mcp (0 stars, last pushed 8mo ago), licensed MIT. It adds 2,452 tokens to every session, about $0.0098 per session on Opus 5.5. 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.

Analytics and metrics Finance and fintech

wrds_mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
wrds_mcp CLAUDE.mdmarianosalinas/wrds_mcp	Instructions file	0	8mo ago	MIT	A	2,452	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

wrds_mcp: Instructions file for Claude Code