What is capture-mcp-server CLAUDE.md?

Repository instructions for developing, building, and running Capture MCP Server, a program that gives Claude tools for accessing federal purchasing and spending data. They describe its TypeScript setup, configuration, and modular design.

Building the server, running it in development or production, configuring it, and understanding its tool categories.

They give an unfamiliar developer the commands and project structure needed to work on the server correctly.

capture-mcp-server CLAUDE.md — Instructions file for coding agents by blencorp: Repository instructions for developing, building, and runnin

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/blencorp/capture-mcp-server/claude-md

Clone the repo

git clone --depth 1 https://github.com/blencorp/capture-mcp-server

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/blencorp/capture-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/blencorp/capture-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/blencorp/capture-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/blencorp/capture-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,563 This file is loaded in full into every session.

When invoked 1,563 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.01563	$0.01563
Opus 5	$0.00781	$0.00781
Sonnet 5	$0.00313	$0.00313
Haiku 4.5	$0.00156	$0.00156

Measured 5d ago against content hash d4840fb09797, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

capture-mcp-server 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 · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Development Commands

Building and Running

npm run build - Compiles TypeScript to dist/ directory
npm start - Runs the compiled server (requires build first)
npm run dev - Development mode with ts-node (auto-reload with nodemon)

Project Configuration

Uses ES modules ("type": "module" in package.json)
TypeScript compilation target: ES2020
Output directory: dist/
Source directory: src/

Architecture Overview

This is a Model Context Protocol (MCP) server that captures federal procurement and spending data through 34 specialized tools. The architecture follows a modular tool-based design:

Core Components

Server (src/server.ts)

MCP server using @modelcontextprotocol/sdk
Uses stdio transport for Claude Desktop integration
Handles tool registration and execution through centralized registry

Tool Architecture (src/tools/)

Modular tool system with six categories:
- reference-tools.ts - 1 static FPDS reference tool (lookup_reference_code; no key, no network)
- sam-tools.ts - 4 SAM.gov API tools (entities, opportunities, details, exclusions)
- usaspending-tools.ts - 6 USASpending.gov API tools (awards, spending, budgets, recipient search, get_award_detail verification, aggregate_contracts grouping)
- tango-tools.ts - 12 Tango API tools (contracts, grants, vendor profiles, opportunities, spending summaries, GAO protests + detail, IDVs + child/task-order drill-down, vehicle catalog, OTAs, entity time-series metrics). Set-aside filtering is exact on FPDS codes; cursor pagination via the Tango next URL.
- highergov-tools.ts - 9 HigherGov tools (forecast/opportunity/contract/people search, saved-search listing, opportunity documents, single-record lookups). Responses are normalized to lowercase agency/vehicle/set-aside slugs via utils/highergov-slugs.ts. get_* tools cache for 15 min in an in-process LRU.
- join-tools.ts - 2 cross-API tools (entity+awards, opportunity+context)
Response conventions (see utils/envelope.ts and docs/fix-plan.md): every list tool echoes filters.upstream vs filters.client_side, nulls untrustworthy totals (total_upstream_unfiltered / total_upstream_unverified + warnings), labels count_unit and date_field, and returns one next_cursor shape. tools/index.ts rejects unknown/mistyped parameters with a structured bad_request. utils/fpds-codes.ts is the FPDS code table; docs/upstream-api-notes.md records which upstream params are verified to bind (run npm run capture-fixtures with live keys to re-probe).
Each tool module exports getTools() and callTool() methods
Central registry in tools/index.ts manages all tool registration

Read the full file on GitHub · 131 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 First seen · 131 lines · 1,563 tokens per session scan A d4840fb09797

Subscribe to this mod's changes

capture-mcp-server CLAUDE.md is an instructions file published in the GitHub repository blencorp/capture-mcp-server (34 stars, last pushed 9d ago), licensed MIT. It adds 1,563 tokens to every session, about $0.0078 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 2026-08-30.

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 · 5,182 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

capture-mcp-server CLAUDE.md