AtlasBurn
Claude connectorCommunityAsk Claude about your AI spend: cost by model and feature, runway forecasts, budget guardrails, and runaway-agent signals. Read-only.
- Tools
- 5
exposed by this connector
Movement
From our daily snapshots over the last 30 days.
Rank by popularity
Rank by trending score
Popularity score
Trending score
In its categories
How this connector compares with others in the same category. Positions are counted within the category, not across the whole directory.
Data analytics1,422nd of 1,936 by popularity · not ranked by trending score
| # | Connector | Popularity | Trending | 7d |
|---|---|---|---|---|
| 1419 | 3,585 | 337places down | ||
| 1420 | 3,585 | 438places down | ||
| 1421 | 3,585 | 134places down | ||
| 1422 | 3,585 | — | ||
| 1423 | 3,585 | — | ||
| 1424 | 3,585 | — | ||
| 1425 | 3,585 | — |
This connector isn’t ranked by trending score, so the category’s top connectors are shown instead.
| # | Connector | Trending | Popularity | 7d |
|---|---|---|---|---|
| 1 | 6,048,830 | — | ||
| 2 | 5,128,156 | — | ||
| 3 | 3,037,347 | — | ||
| 4 | 2,221,248 | 21places up | ||
| 5 | 2,079,337 | — | ||
| 6 | 1,956,519 | 9places down | ||
| 7 | 1,503,432 | 18places up |
Developer tools686th of 934 by popularity · not ranked by trending score
| # | Connector | Popularity | Trending | 7d |
|---|---|---|---|---|
| 683 | 3,700 | 465places down | ||
| 684 | 3,700 | 279places down | ||
| 685 | 3,585 | 337places down | ||
| 686 | 3,585 | — | ||
| 687 | 3,585 | — | ||
| 688 | 3,585 | 337places down | ||
| 689 | 3,585 | 493places down |
This connector isn’t ranked by trending score, so the category’s top connectors are shown instead.
| # | Connector | Trending | Popularity | 7d |
|---|---|---|---|---|
| 1 | 8,217,214 | — | ||
| 2 | 5,128,156 | — | ||
| 3 | 3,037,347 | — | ||
| 4 | 2,508,810 | — | ||
| 5 | 1,956,519 | 9places down | ||
| 6 | 1,271,178 | 1places down | ||
| 7 | 914,345 | — |
AtlasBurn connects Claude to your real AI usage and cost data so you can ask where your LLM spend is going and catch problems before they become a large bill.
What you can ask:
- Total AI spend, token usage, and request volume over any window
- Cost broken down by model and by product feature, so you can see what is actually driving the bill
- Projected monthly bill, current daily burn, and budget runway
- Guardrail status: whether budgets are enabled, the enforcement state (active, throttled, or suspended), configured daily and hourly limits, and recent breaches
- Runtime signals such as retry rate, loop probability, and context growth, to spot an agent stuck in a retry loop or running away
AtlasBurn works across OpenAI, Anthropic, Google Gemini, and other providers. Telemetry comes from the AtlasBurn SDK or edge proxy that you add to your app.
The connector is read-only and content-blind: it reads cost and usage telemetry from your AtlasBurn workspace, never changes your settings or budgets, and never sees your prompts or model outputs. Sign-in uses OAuth with your AtlasBurn account, and access is scoped to your own organization's data.
Tools
- get_cost_breakdown
- get_cost_summary
- get_guardrail_status
- get_runtime_signals
- get_runway_forecast
- Categories
- Sign-in
- Required
- Connector URL
- https://app.atlasburn.com/api/mcp
- Transport
- Streamable HTTP
- Works with
- Claude, Claude API, Claude Code, Claude Desktop
- Added
- October 8, 2026
- More info