"Actual Budget" matching MCP servers:

Pay-per-call USDC payment proxy for AI agents. Issue scoped Pay Tokens with hard spending caps and auto-journal every charge to freee / Money Forward / QuickBooks.

Enables a Claude Code agent to fetch remaining 5-hour and weekly subscription usage limits, reset times, and per-window breakdowns as JSON. It provides the same figures as /usage through a local, read-only tool.

MCP server scaffold for budget tooling, currently only provides a placeholder ping tool returning 'pong' to confirm plumbing works. No real budget functionality yet.

Budget & cost control for AI agents: hard per-agent spend caps, rate limits, idempotency, and human-in-the-loop approval — enforced before each LLM call, not after the invoice. One hosted MCP endpoint (no proxy or self-hosting), settled via x402 (USDC on Base).

Model-agnostic code memory MCP server using budget-aware graph retrieval for AI agents, providing sub-millisecond queries, token budgeting, and deterministic results without embeddings or vector databases.

Enables auditing MCP servers' tools by their estimated context token cost, ranking verbose names, descriptions, and schemas before they consume the agent window. Can run as an MCP tool so agents can budget their own context.

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.

Enables calculating PagedAttention KV cache allocation and GPU memory budgets for vLLM-style chunked prefill workloads via MCP.

Enables AI coding agents to list, read, create, update, delete, and render PlantUML and Mermaid diagrams, and check them against the actual codebase to detect architecture drift.

Compiler introspection for the Hirð language (typed actors and effect rows on the BEAM): type inference, definition lookup, effect-row explanation, IR fragments, actor protocol and supervision graphs, and token-budget-aware symbol summaries.

Provides constraint satisfaction and optimization capabilities to LLMs and AI agents for scheduling, resource allocation, routing, budget optimization, and configuration problems using Google OR-Tools CP-SAT solver.

Serves token-efficient code context for AI coding assistants by exposing Python signatures, call graphs, and budget-packed task context as MCP tools, enabling precise codebase queries without reading entire files.

Multi-agent swarm orchestrator for AI workflows. Exposes blackboard read/write, agent dispatch, permission gating (AuthGuardian), token budget enforcement (FederatedBudget), and audit log tools over MCP. Supports 14 AI framework adapters including LangChain, AutoGen, CrewAI, Codex, and A2A — mix any frameworks in one swarm with race-condition-safe shared state.(Traffic light for agents)

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.

Loads your project's Tailwind CSS config and exposes tools for AI agents to query actual design tokens and validate class names, preventing hallucination of non-existent utilities.

Audits coding agents' claimed actions against the actual Git working tree, blocking completion if any claimed changes are unverified.

Analyzes all permission settings files for coding agents, showing which settings take precedence and identifying rules that are accepted but ignored. Helps users understand and debug their agent's actual permission behavior.

Assesses code change risk with ultra-low token budget (50-100 tokens) and provides structured risk metadata for AI agents in IDEs.

Provides role-aware repository maps for LLM agents by analyzing codebases and ranking files within a token budget.