agentmods.dev

awesome-mcp-servers: Instructions file for Claude Code

CLAUDE.md

awesome-mcp-servers CLAUDE.md is an instructions file for Claude Code from Sagargupta16/awesome-mcp-servers. It costs 4,894 tokens per session, scanned A, original, CC0-1.0.

Repository-specific instructions for contributing to an open list of MCP servers, frameworks, clients, and resources. The repository is a Markdown-only project whose content is displayed directly on GitHub.

In plain words
What is it for?
They help edit README.md, understand the repository structure, and run the optional lychee link checker, which checks whether links still work.
Why use it?
They tell an agent where the project’s rules and files are, what commands are relevant, and how to check links before submitting changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Gemini CLI.

This is Sagargupta16/awesome-mcp-servers's own configuration. It tells Claude Code how to work on awesome-mcp-servers itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything awesome-mcp-servers configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is - Root [`CLAUDE.md`](../../CLAUDE.md) -- voice, rules, routing map, references, skills, slash commands, conventions..

not rated 57repo +20 changed 12d ago A scan 4,894 tokens original CC0-1.0
View source ↗ Sagargupta16/awesome-mcp-servers sagargupta.online
Reuse

Borrowing it

Nothing to install: this file belongs to Sagargupta16/awesome-mcp-servers. 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/Sagargupta16/awesome-mcp-servers/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Sagargupta16/awesome-mcp-servers

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.

agentmods badge for awesome-mcp-servers CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sagargupta16/awesome-mcp-servers/claude-md/github.svg)](https://agentmods.dev/instructions/sagargupta16/awesome-mcp-servers/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sagargupta16/awesome-mcp-servers/claude-md"><img src="https://agentmods.dev/badge/instructions/sagargupta16/awesome-mcp-servers/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.

agentmods 80×15 button for awesome-mcp-servers CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sagargupta16/awesome-mcp-servers/claude-md"><img src="https://agentmods.dev/badge/instructions/sagargupta16/awesome-mcp-servers/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,894 This file is loaded in full into every session.
When invoked 4,894 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04894 $0.04894
Opus 5.5 $0.01958 $0.01958
Sonnet 5.5 $0.00979 $0.00979
Haiku 4.5 $0.00489 $0.00489

Measured 12d ago against content hash a593fcbfec10, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

awesome-mcp-servers CLAUDE.md scanned grade A 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `Remote` rows skip the licence, 180-day and stub checks and are judged on CONTRIBUTING's "Hosted servers" rules instead. The gate finds the endpoint in the docs page or the repo README and `server.json`, POSTs an MCP `
CLAUDE.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file stacks on top of the workspace root at C:\Code\GitHub\:

  • Root CLAUDE.md -- voice, rules, routing map, references, skills, slash commands, conventions.
  • Root MEMORY.md -- live facts across repos.
  • Root STATUS.md -- live PR/CI/security dashboard.
  • .claude/resources/ -- deep reference for collaboration, workflow, git, OSS, debugging, voice.

Read those first. The guidance below only adds repo-specific context -- it does not override anything in the root.

Project

Curated awesome-list of MCP servers, frameworks, clients, and resources, maintained by Sagar and open to community PRs. README.md is the product; scripts/ is the machinery that keeps its promises true.

Stack

  • Language: Markdown (the list) plus Python (the gate scripts in scripts/, stdlib only)
  • Framework: none
  • Database: none
  • Package manager: none for the list; requirements-dev.in / requirements-dev.txt hash-lock ruff and pytest for the scripts
  • Deploy target: the GitHub README, plus a static site on GitHub Pages built from it by scripts/build_site.py (site/ holds the template, CSS and JS; output _site/ is gitignored)

Run

python scripts/validate.py          # structure, format, duplicates, conflict markers (ordering is a note)
python scripts/validate.py --fix    # auto-repair ordering, table alignment, whitespace, dashes; refuses a file with conflict markers
npx --yes awesome-lint README.md     # sindresorhus/awesome's linter; pass the RELATIVE name (an absolute C:\ path reads as a URL)
GITHUB_TOKEN=$(gh auth token) python scripts/check_submission.py --base-ref origin/main
python scripts/check_new_links.py --base-ref origin/main   # only the links a change adds
GITHUB_TOKEN=$(gh auth token) python scripts/thank_contributors.py --dry-run   # who the thank-you bot would comment on
GITHUB_TOKEN=$(gh auth token) python scripts/staleness_report.py
GITHUB_TOKEN=$(gh auth token) python scripts/build_site.py      # site into _site/; without a token it builds with no stars
python -m http.server 8766 --directory _site                   # preview it

Read the full file on GitHub · 107 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.

  1. 12d ago Changed · +167 tokens per session a593fcbfec10
  2. 13d ago Changed · +2 lines · +576 tokens per session 3730904a7f42
  3. 15d ago Changed · +1 lines · +57 tokens per session 19fc650d8027
  4. 16d ago Changed · +236 tokens per session e5660a410c03
  5. 18d ago Changed · +3 lines · +512 tokens per session 80e159dc0937
  6. 23d ago Changed · +8 lines · +801 tokens per session c6e09f2cfd13
  7. 1mo ago Changed · +1 lines · +140 tokens per session c74f940d44e7
  8. 1mo ago Changed · +4 lines · +354 tokens per session 41abcc0c2d04
  9. 1mo ago Changed · +31 tokens per session 4d614110a1da
  10. 1mo ago First seen · 88 lines · 2,020 tokens per session scan A 3ed7e5b296a8

Subscribe to this mod's changes

awesome-mcp-servers CLAUDE.md is an instructions file published in the GitHub repository Sagargupta16/awesome-mcp-servers (57 stars, last pushed today), licensed CC0-1.0. It adds 4,894 tokens to every session, about $0.0196 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

LLMaiai-toolsawesomeawesome-listclaude
Related

awesome-mcp-servers CLAUDE.md compared with instructions from other repositories

awesome-mcp-servers CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
awesome-mcp-servers CLAUDE.mdSagargupta16/awesome-mcp-serversInstructions file57todayCC0-1.0A4,894Claude Code
awesome-ai-rules copilot-instructions.mdshumatsumonobu/awesome-ai-rulesInstructions file13mo agoMITA236GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot