Claude MarketplacesSubmit
mukundakatta avatar

Promptbudget Mcp

mukundakatta/mcp-stack

Exposes a single tool, `truncate_to_token_budget`, that lets Claude count tokens and fit text into a context window mid-task without hallucinating character offsets or chunk boundaries. The logic is ported from the author's `promptbudget` Rust crate but implemented in plain JavaScript so you don't need a toolchain. Useful when you're chaining prompts, building RAG pipelines, or need deterministic truncation that respects token limits rather than guessing at string slices. Part of a fourteen-server collection that replaces operations LLMs commonly fumble,regex, CSV parsing, timezone math,with real implementations they can call as tools.

tool
1
transport
STDIO
last updated
May 11, 2026
View on GitHub

Tools

1 tools

Public tool metadata for what this MCP can expose to an agent.

truncate_to_token_budgetLLM needs to fit text into a context window mid-task

LLM needs to fit text into a context window mid-task

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Readme

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

PackageToolsWhen to install
@mukundakatta/promptbudget-mcptruncate_to_token_budgetLLM needs to fit text into a context window mid-task
@mukundakatta/citecite-mcpinject_citations, parse_citations, strip_citationsRound-trip [1] [2] markers in RAG outputs
@mukundakatta/ragmetric-mcprecall_at_k, hit_at_k, mrr, ndcg_at_k, evaluate_batchLLM helps score retrieval quality
@mukundakatta/ragdrift-mcpinterpret_drift_score, recommend_thresholds, explain_drift_dimensionsLLM diagnoses RAG drift alerts

Reliable transforms LLMs reach for tools instead of imagining

View the full README on GitHub

Details

Repository
github.com/mukundakatta/mcp-stack
Category
AI & LLM Tools
Package
@mukundakatta/promptbudget-mcp
Transport
STDIO
Registry
MCP registry, active

More from mukundakatta

Related AI & LLM Tools MCP servers

View all
1mukundakatta avatarRagdrift Mcpmukundakatta/mcp-stackDiagnose RAG drift: interpret scores, recommend thresholds, explain dimensions.0stars
2patrickbakowski avatarAgentDilemmapatrickbakowski/agent-dilemma-skillSubmit a dilemma for blind community verdict with reasoning to improve low confidence0stars
3ryvonetwork avatarRyvo Protocolryvonetwork/ryvo-agenticMCP server for Ryvo Protocol state reads and prepare-only payment-channel actions.0stars
4skibuff22 avatarPublish Gate (lite)skibuff22/agent-ops-kit-liteCheck a draft's numbers against your facts.md and its links before you publish.0stars
5thelabvenice avatarMemdatathelabvenice/memdata-mcpPersistent memory for AI agents. Store context, retrieve it semantically.0stars
6vktr93 avatarReviewmetricvktr93/reviewmetric-mcpAn MCP server connecting Claude to the Review Metric 15-agent scientific peer review pipeline.0stars