Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
6,000+ web scrapers for your AI agent, start free logo6,000+ web scrapers for your AI agent, start free

Apify gives your agent live web data: 6,000+ prebuilt scrapers and actors, MCP-ready. Sign up free with $5 in usage credits.

Try Apify free
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 48,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

Inject, parse, and strip [N] citation markers in RAG outputs.

README.md

mcp-stack

Fourteen small MCP servers for everyday LLM / RAG / agent work. Each ships independently on npm, listed in the official MCP Registry, and is callable from Claude Desktop, Cursor, Cline, Windsurf, Zed, and any other MCP-compatible client.

RAG / agent helpers

| Package | Tools | When to install | |---|---|---| | @mukundakatta/promptbudget-mcp | truncate_to_token_budget | LLM needs to fit text into a context window mid-task | | @mukundakatta/citecite-mcp | inject_citations, parse_citations, strip_citations | Round-trip [1] [2] markers in RAG outputs | | @mukundakatta/ragmetric-mcp | recall_at_k, hit_at_k, mrr, ndcg_at_k, evaluate_batch | LLM helps score retrieval quality | | @mukundakatta/ragdrift-mcp | interpret_drift_score, recommend_thresholds, explain_drift_dimensions | LLM diagnoses RAG drift alerts |

Reliable transforms LLMs reach for tools instead of imagining

| Package | Tools | When to install | |---|---|---| | @mukundakatta/csv-tools-mcp | parse_csv, to_csv, pluck_columns | LLM needs RFC 4180-correct CSV (quoted fields, embedded commas, BOMs) | | @mukundakatta/regex-test-mcp | test_regex, find_all, replace | LLM needs exact regex semantics with real match offsets and named groups | | @mukundakatta/jmespath-mcp | json_query | LLM needs deep JSON traversal (filters, projections, pipes) without hallucinating | | @mukundakatta/diff-mcp | unified_diff, apply_patch, parse_patch | Code-review or code-edit agent needs character-precise patches | | @mukundakatta/sqlfmt-mcp | format_sql, list_dialects | Deterministic SQL formatting across 19 dialects | | @mukundakatta/shellquote-mcp | quote_bash, quote_bash_argv, quote_cmd, quote_powershell | Safe shell argument escaping; LLMs constantly mishandle quotes/$VAR | | @mukundakatta/json5-mcp | parse_json5, to_json5, to_strict_json | LLM emitted JSON-with-comments / trailing-commas; round-trip to strict JSON | | @mukundakatta/toml-yaml-json-mcp | parse, format, convert | TOML / YAML / JSON conversion (LLMs especially mishandle TOML) | | @mukundakatta/timezone-mcp | convert_tz, now_in, tz_offset | IANA timezone math with real DST rules; LLMs hallucinate offsets | | @mukundakatta/html-to-markdown-mcp | html_to_md, extract_text | Web-scraping agents need clean Markdown / text from HTML |

Sibling libraries

The first four wrap or re-implement logic from the user's Rust + Python work:

ragdrift-py (PyPI) — five-dimensional drift detection

stopstream, citecite, ragmetric — pure-Rust crates from the rust-llm-stack workspace

The MCP servers are independent: they implement the logic they need in plain JavaScript so installing them doesn't pull a Rust toolchain.

Install (any of them)

Add to your MCP client config. Example for Claude Desktop:

{
  "mcpServers": {
    "promptbudget": { "command": "npx", "args": ["-y", "@mukundakatta/promptbudget-mcp"] },
    "citecite":     { "command": "npx", "args": ["-y", "@mukundakatta/citecite-mcp"] },
    "ragmetric":    { "command": "npx", "args": ["-y", "@mukundakatta/ragmetric-mcp"] },
    "ragdrift":     { "command": "npx", "args": ["-y", "@mukundakatta/ragdrift-mcp"] },
    "csv-tools":    { "command": "npx", "args": ["-y", "@mukundakatta/csv-tools-mcp"] },
    "regex-test":   { "command": "npx", "args": ["-y", "@mukundakatta/regex-test-mcp"] },
    "jmespath":     { "command": "npx", "args": ["-y", "@mukundakatta/jmespath-mcp"] },
    "diff":           { "command": "npx", "args": ["-y", "@mukundakatta/diff-mcp"] },
    "sqlfmt":         { "command": "npx", "args": ["-y", "@mukundakatta/sqlfmt-mcp"] },
    "shellquote":     { "command": "npx", "args": ["-y", "@mukundakatta/shellquote-mcp"] },
    "json5":          { "command": "npx", "args": ["-y", "@mukundakatta/json5-mcp"] },
    "toml-yaml-json": { "command": "npx", "args": ["-y", "@mukundakatta/toml-yaml-json-mcp"] },
    "timezone":       { "command": "npx", "args": ["-y", "@mukundakatta/timezone-mcp"] },
    "html-to-md":     { "command": "npx", "args": ["-y", "@mukundakatta/html-to-markdown-mcp"] }
  }
}

Develop

git clone https://github.com/MukundaKatta/mcp-stack
cd mcp-stack
npm install
npm test --workspaces

License

MIT OR Apache-2.0.

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use Vector & Memory servers.