mcp server
BurnRate
⚡ Terminal HUD, hard budget breakers & prompt-cache leak alerts for AI coding agents (Claude Code, Cursor, Codex)
Set up
Runs on your computer. Pick your agent and operating system.
This project does not publish an install method we can turn into a config. Follow the README instead.
README
synced Oct 25, 2026██████╗ ██╗ ██╗██████╗ ███╗ ██╗██████╗ █████╗ ████████╗███████╗
██╔══██╗██║ ██║██╔══██╗████╗ ██║██╔══██╗██╔══██╗╚══██╔══╝██╔════╝
██████╔╝██║ ██║██████╔╝██╔██╗ ██║██████╔╝███████║ ██║ █████╗
██╔══██╗██║ ██║██╔══██╗██║╚██╗██║██╔══██╗██╔══██║ ██║ ██╔══╝
██████╔╝╚██████╔╝██║ ██║██║ ╚████║██║ ██║██║ ██║ ██║ ███████╗
╚═════╝ ╚═════╝ ╚═╝ ╚═╝╚═╝ ╚═══╝╚═╝ ╚═╝╚═╝ ╚═╝ ╚═╝ ╚══════╝
Terminal HUD, Hard Spend Caps & Cache Guard for Coding Agents
Never wake up to an unexpected $40 Claude Code or Cursor bill again.
A lightweight, zero-overhead reverse proxy and CLI HUD that gives developers absolute cost control and prompt-cache leak alerts over autonomous AI sessions.
🎯 The Problem: Why Developers Fear Agent Bills
Software engineers adopting autonomous terminal coding assistants (Claude Code, Cursor, Codex, OpenCode, Aider) frequently suffer from bill anxiety:
- Silent Infinite Retry Loops: An agent gets confused by a compiler or test error and loops 35 times, burning $15 in 4 minutes.
- Context Explosions: The agent inadvertently reads
package-lock.json,dist/, or a 10MB SQLite database into context. - Prompt Cache Breakage: A tiny dynamic timestamp or un-sorted JSON injected at the top of a prompt secretly invalidates the 90% prompt cache discount, multiplying token costs by 10x with zero warning.
burnrate acts as an in-line cost shield: a zero-latency reverse proxy and terminal HUD that monitors session spend and terminates runaway loops before they drain your wallet.
🖥️ Live Terminal Status HUD
Renders directly to stderr with live cost consumption, token burn rates, and prompt-cache health:
┌─────────────────────────────────────────────────────────────────────────────┐
│ burnrate │ Session: $0.42 / $2.00 max │ Burn: $0.08/min │ Cache: 92.1% │
│ Tokens: 18.4k total │ Turns: 6 │ Status: OPTIMAL (Prompt Cache Warm) │
└─────────────────────────────────────────────────────────────────────────────┘
🏛️ System Architecture
+-----------------------------------------------------------------------------------+
| Coding Agent CLI (Claude Code, Cursor, Codex, OpenCode) |
| `export ANTHROPIC_BASE_URL=http://localhost:7070` |
+-----------------------------------------------------------------------------------+
|
| Streaming HTTP Request
v
+-----------------------------------------------------------------------------------+
| `burnrate` Proxy (Rust Axum) |
| |
| [ Feature 1: Hard Budget Circuit Breaker ] |
| - If `session_cost >= max_spend` (e.g. $1.50): |
| * Terminate connection immediately with HTTP 402 Payment Required |
| * Emits diagnostic: "burnrate: Budget cap reached ($1.50). Session halted." |
| |
| [ Feature 2: Prompt-Cache Invalidation Linter ] |
| - Computes byte-level prefix hash diffs between Turn N-1 and Turn N: |
| * If early prefix bytes drift (e.g. timestamp injected at byte 0), |
| flashes warning: "⚠️ Cache busted at byte 18: prefix drift detected" |
| |
| [ Feature 3: In-Line Secret Guard & Token Redactor ] |
| - Scans outbound prompts for OpenAI, Anthropic, AWS, and GitHub credentials |
| * Masks leaked tokens with `[REDACTED_BY_BURNRATE:<TYPE>]` before forwarding |
| |
| [ Feature 4: Live Terminal HUD ] |
| - Real-time spend tracking ($/min burn, cache hit ratio, token breakdown) |
+-----------------------------------------------------------------------------------+
|
| Forward to Upstream
v
+-----------------------------------------------------------------------------------+
| Official Provider API (Anthropic, OpenAI, DeepSeek) |
+-----------------------------------------------------------------------------------+
🚀 Quickstart
1. Installation
cargo install burnrate-agent
# Or build from source:
git clone https://github.com/ronitgupta138/burnrate.git
cd burnrate && cargo build --release
2. Wrap Any Agent Command (Hard Cap Mode)
Wrap your agent with a strict budget limit (e.g., $2.00):
# Wrap Claude Code
burnrate run --max-spend 2.00 -- claude
# Wrap OpenCode or Codex
burnrate run --max-spend 1.50 -- opencode
3. Run Standalone Proxy Daemon
Start the proxy daemon in a dedicated tmux pane:
burnrate serve --port 7070 --max-spend 3.00
In your development terminal:
export ANTHROPIC_BASE_URL="http://127.0.0.1:7070"
export OPENAI_BASE_URL="http://127.0.0.1:7070"
📊 Supported Model Pricing Tables
burnrate maintains exact pricing tables factoring in 90% prompt-cache read discounts:
| Model Family | Input / MTok | Output / MTok | Cache Read (90% off) | Cache Write |
|---|---|---|---|---|
| Claude 3.7 / 3.5 Sonnet | $3.00 | $15.00 | $0.30 | $3.75 |
| Claude 3.5 Opus | $15.00 | $75.00 | $1.50 | $18.75 |
| Claude 3.5 Haiku | $0.80 | $4.00 | $0.08 | $1.00 |
| GPT-4o | $2.50 | $10.00 | $1.25 | $2.50 |
| GPT-4o-mini | $0.15 | $0.60 | $0.075 | $0.15 |
| DeepSeek-V3 | $0.14 | $0.28 | $0.014 | $0.14 |
🧪 Verification & Benchmarks
cargo test
running 31 tests
test adapter::tests::test_openai_to_anthropic_response_translation ... ok
test adapter::tests::test_anthropic_to_openai_translation ... ok
test cache_engine::tests::test_cache_breakpoint_injection_on_large_system_prompt ... ok
test config::tests::test_config_defaults_and_serialization ... ok
test cache_engine::tests::test_cache_bypass_on_small_payload ... ok
test fallback::tests::test_fallback_trigger_at_95_percent_spend ... ok
test policy::tests::test_policy_engine_rule_enforcement ... ok
test vault::tests::test_token_vault_injection ... ok
test web::tests::test_embedded_dashboard_html_validity ... ok
test context_guard::tests::test_lockfile_truncation ... ok
test secret_guard::tests::test_secret_guard_unit ... ok
test ledger::tests::test_ledger_record_and_summary ... ok
test test_local_fallback_decision_logic ... ok
test test_schema_adapter_full_translation_loop ... ok
test test_proxy_fallback_header_when_spend_critical ... ok
test test_cache_engine_breakpoint_injection ... ok
test test_proxy_end_to_end_context_truncation_and_cache_injection ... ok
test test_context_window_guard_thresholds ... ok
test test_budget_governor_hard_spend_breaker ... ok
test test_pricing_calculation ... ok
test test_prompt_cache_invalidation_linter ... ok
test test_terminal_hud_rendering ... ok
test test_proxy_budget_enforcement_endpoint ... ok
test test_config_load_and_serialization ... ok
test test_ledger_record_and_summary_lifecycle ... ok
test test_proxy_integration_records_to_ledger ... ok
test test_mcp_initialize_and_tool_list ... ok
test test_mcp_call_status_tool ... ok
test test_prometheus_metrics_export ... ok
test test_model_cost_router_downgrade_on_low_budget ... ok
test test_proxy_secret_redaction_header_and_body ... ok
test test_secret_guard_all_credential_types ... ok
test test_streaming_token_counter_ingestion ... ok
test test_swarm_role_partitioning_and_summary ... ok
test test_proxy_multi_agent_swarm_header_enforcement ... ok
test test_policy_engine_custom_rules_and_verdict ... ok
test test_token_vault_key_injection ... ok
test test_proxy_v2_kernel_dashboard_and_policy_enforcement ... ok
test test_team_budget_pool_multi_agent_partitioning ... ok
test test_velocity_brake_threshold_enforcement ... ok
test result: ok. 31 passed; 0 failed; 0 ignored; finished in 0.01s
💖 Sponsoring & Supporting Development
burnrate is an independent open-source project built to protect developers, teams, and autonomous agent harnesses from accidental $100+ API bill explosions and silent prompt-cache invalidation leaks.
If burnrate has saved your team from runaway token invoices or improved your agent infrastructure, consider sponsoring development on GitHub:
- ☕ Backers ($5–$10/mo): Named credit in official release notes and README backer roll.
- ⚡ Power Users & Teams ($25/mo): Direct influence on roadmap RFCs and priority feature triage.
- 🏢 Organization Sponsors ($100/mo): Prominent company logo and link displayed on README and dashboard.
📜 License
MIT License. Designed and engineered by Ronit Gupta.