"Actual Budget" matching MCP servers:

Budget Planner AI - MCP server providing AI-powered tools and automation by MEOK AI Labs

Enables agents to monitor running loops, estimate token consumption and monetary cost, prune verbose thinking chains near limits, and route sub-tasks between fast/cheap models and deep reasoning engines. It provides budget-aware model routing and telemetry through MCP.

MCP server for estimating LLM token consumption and costs from project documents, code, and materials. Provides 8 tools including project budget planning, token/cost estimation, GitHub repo analysis, and pricing refresh.

Lets Claude Desktop, Cursor, Cline, Windsurf, Zed, or any other MCP client estimate token counts and fit a chat history into a model's context budget on demand.

Static worst-case token-budget analysis for LLM-agent workflows using AST analysis to identify certifiable, default-dependent, non-certifiable, and runaway units, with optional signed budget certificates.

Enables AI assistants to drive a Google Flow web workspace through local login-session reuse: inspecting the account's actual models and parameters, submitting image and video generation jobs, tracking each job by persistent ID, and downloading the matching media to a specified local path with file and parameter records. Supports repeatable, multi-shot video production workflows where tracked assets are handed off to editing tools like FFmpeg.

Enables Claude Code to offload bulk tasks to cheap OpenRouter worker models via tiered model selection, parallel batch execution, daily budget caps, and cost logging.

Connects a text-only coding agent to an OpenAI-compatible vision model so it can analyze images, screenshots, and UI mockups. Provides tools for general image understanding, OCR and code transcription, error-screenshot diagnosis, technical diagram and chart interpretation, UI-to-code/spec generation, and expected-versus-actual UI comparison.

Enables agents to query the TypeSafe Jev decision model for typed answers—yes/no, choice, and score questions—with calibrated probabilities, batched in a single request under a local context-budget guard.

Enables teams to measure their actual ticket-writing style from GitLab, Jira, or GitHub and check new or draft tickets against that learned house profile, with optional model-backed drafting.

Local MCP server that plans, generates, and assembles production assets (images, audio, video) through multi-agent personas and official APIs, with free-tier budget guard.

Cross-platform ad management MCP server for Google Ads and Meta Ads. Campaign analytics, A/B testing with z-test, anomaly detection, and budget reallocation. 15 tools, 60 tests.

MCP server for Decixa that helps AI agents find and resolve APIs for tasks using natural language intents, with support for budget and latency filtering.

VibOps MCP is the control plane between your AI agents and your GPU infrastructure. 74 tools covering: GPU fleet management (deploy, scale, monitor across NVIDIA, AMD, Intel, AWS, Google, Groq), Agent Infrastructure Control Plane (per-agent GPU cost, budget enforcement, model policies, dependency graph), governance (AI Act, SOC 2, immutable HMAC audit chain), and GPU FinOps (chargeback, waste..)..

Enables agents and developers to estimate, budget, and compare LLM spend per task before and during a run, including ranking models by expected cost per successful task and tracking spend in a local JSON ledger.

Enables AI agents and Claude Code to generate Midjourney images, wait for jobs to finish, download the actual image files, and create reusable moodboards through a signed-in Chrome session without API keys.

Enables AI assistants to interact with Bayesian marketing mix models through natural language, including data upload, model building, result inspection, budget optimization, and scenario planning.

Enterprise AI governance layer for spend tracking, runtime guardrails, policy enforcement, and budget limits. Connects Claude, ChatGPT, and any MCP client to ThinkNEO's control plane for SOC2/GDPR/HIPAA compliance monitoring and real-time provider health.

Enables local Codex users to generate and preview images, music, video, and speech, with model catalogs, cost estimates, budget validation, task recovery, and account-scoped media handling.

Enables Claude to generate ByteDance Seedance videos and Seedream images through a BytePlus key, pricing every request in dollars before it is sent. It adds budget limits, ask-first approvals and whole-key spend tracking so costly generations cannot happen without consent.

Routes your AI tasks to the best available model across 20+ providers — automatically selecting based on task type, budget, and subscription pressure. Supports text, image, video, and audio with built-in cost optimization and fallback chains.

Webhound is a research engine with an explicit effort control: a prompt defines the investigation and a dollar budget defines how much work it deserves. It returns cited reports or sourced datasets with the working documents, claims, sources, limitations, and evidence pack behind the answer.

An intelligent, agentic MCP server gateway to OpenRouter's 200+ AI models. It provides budget controls, security features, semantic memory, and code search capabilities.

AI-powered travel route planning server with budget estimation, packing suggestions, and food recommendations, using LangChain reactive agent with Tongyi Qwen and local deterministic fallback tools.

Enables LLM clients to select the most relevant MCP tools from a catalog within a context-token budget, without executing them or shipping keys.

Enables screening LLM input and output through cost-tiered safety checks with per-tenant budgets, returning allow, block, or review decisions. It exposes a JSON-RPC screen tool that isolates tenant spend and falls back to a configurable policy on provider failure or budget exhaustion.

MCP server that routes AI chat requests to the best available provider (Anthropic, OpenAI, Groq, etc.) with automatic fallback, budget caps, and model-tier routing.

Enables AI agents to work with a GPU cloud: check live GPU prices, launch GPUs on ready images, run commands as jobs that stop billing when the command exits, schedule runs, move files, and check spend. Access is scoped to one signed-in environment and capped by its monthly budget.

Enables AI agents and MCP clients to dispatch queries to the most suitable model among 70+ LLMs by scoring intent, budget, cost, and latency, returning structured routing decisions with execution telemetry. It runs as a zero-dependency Python MCP server that plugs into Claude Desktop, Cursor, and other MCP-compatible clients.

MCP server for deterministic, zero-dependency context-window math, enabling token estimation, text truncation, and budget reporting without a tokenizer.