MCP.Market

Promptbudget MCP server

by MukundaKatta·io.github.MukundaKatta/promptbudget-mcp·v0.2.0
No reviews yet

Token-budget-aware text handling: count, truncate, and chunk for LLM prompts.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

0 stars28 downloads/wk

Reviews

Write one

Nobody has reviewed Promptbudget yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Promptbudget tools (3, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • chunk_to_budget

    Split a long text into multiple chunks, each at most max_tokens tokens, with optional overlap between adjacent chunks. Use when you have source material too long for one prompt and want to feed it through in pieces (for example, RAG ingestion or a fan-out summarize pattern). Overlap is useful so a sentence at a boundary still has surrounding context in the next chunk.

  • count_tokens

    Count the approximate token usage of a text. Optionally compare against a budget and return a 'fits' flag plus overflow. Use as a pre-flight check before assembling a prompt: if count > budget, decide whether to truncate or chunk.

  • truncate_to_token_budgetwrite action

    Truncate text to fit within a token budget. Four strategies: head (keep beginning), tail (keep end, good for chat history), head_tail (drop the middle, keep both ends), and smart_cut (head_tail with a visible cut marker). Use when you need to put long text into an LLM context window without going over a token limit.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan3 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 29 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Promptbudget compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 90% of 4,464 AI and agents servers
Tools
3
the typical AI and agents server has 6
Tools that change things
33%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
28
more than 15% of 1,515 AI and agents servers with a package

What its tools let an agent do: 2 read · 1 change

Install Promptbudget in Claude Code, Cursor or VS Code

Runs npx -y @mukundakatta/promptbudget-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add promptbudget-mcp -- npx -y @mukundakatta/promptbudget-mcp
Add to Cursor

What the publisher says

From the Promptbudget repository's README, as published. We do not edit it. Read it on GitHub

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

Reliable transforms LLMs reach for tools instead of imagining

Sibling libraries

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

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

  • ragdrift (crates.io) /

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

  • embedrank, promptbudget,

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:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Promptbudget: common questions

Is Promptbudget MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Promptbudget safety report
How do I install Promptbudget?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Promptbudget need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Promptbudget maintained?
The last commit was 65 days ago (2026-08-29). The latest release is v0.2.0.
What can I use instead of Promptbudget?
Servers from other publishers that do the same job: llmtrim MCP server, PaperBanana MCP server and Commonly MCP server.
How does Promptbudget compare with other AI and agents MCP servers?
safety score 92/100 (higher than 90% of 4,464 AI and agents servers); tools 3 (the typical AI and agents server has 6); tools that change things 33% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Promptbudget

Same job from other publishers: the closest match first, then the best rated.

  • llmtrim
    MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
    A
  • PaperBanana
    Generate academic diagrams and statistical plots from text using multi-agent AI.
    A
  • Commonly
    Read Commonly pods and post as a Commonly agent you create, with a token from your Commonly account.
    A
  • Agent-Native Analytics
    Agent-Native Amplitude/Mixpanel - connect data sources, prompt for charts
    A
  • mcptoon
    MCP tools + agent skills in one zero-dependency CLI: 71,929 -> 581 tokens (-99.2%, measured).
    A

More from MukundaKatta →