agentburn
PYPI · AGENTBURN · SCANNED SEP 20
Local profiler: which usage window took you out, and where your agent's money goes
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
- No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 14 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability77
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 710 tokens (~118/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management80
- Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the agentburn MCP server?
agentburn runs locally as a PyPI package, launched with uvx agentburn. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · agentburn
claude mcp add socialpranker-agentburn -- uvx agentburn
{
"mcpServers": {
"socialpranker-agentburn": {
"command": "uvx",
"args": [
"agentburn"
]
}
}
} {
"servers": {
"socialpranker-agentburn": {
"command": "uvx",
"args": [
"agentburn"
]
}
}
} codex mcp add socialpranker-agentburn -- uvx agentburn
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"socialpranker-agentburn": {
"type": "local",
"command": [
"uvx",
"agentburn"
],
"enabled": true
}
}
} openclaw mcp add socialpranker-agentburn --command uvx --arg agentburn
mcp_servers:
socialpranker-agentburn:
command: "uvx"
args: ["agentburn"] {
"McpServers": {
"socialpranker-agentburn": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"agentburn"
]
}
}
} assistant mcp add socialpranker-agentburn -t stdio -c uvx -a agentburn
{
"mcpServers": {
"socialpranker-agentburn": {
"command": "uvx",
"args": [
"agentburn"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Sept 26 −3
- Stability: pass → 0.80 functional
- 19 Sept 26 +1
- Stability: 0.97 → pass security
- 17 Sept 26 +1
- Package version: 0.12.3 → 0.14.0 functional
- 15 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Sept 26 −3
- Stability: pass → 0.80 functional
- 12 Sept 26 +1
- Stability: 0.97 → pass security
- 10 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 8 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed pypi/agentburn@0.14.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 0 packages
| Packages resolved | 0 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
burn_card ~88
Anonymized shareable burn summary (plain text, safe to post).
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | – | hermes | openclaw | claude-code (default: first detected) |
| days | integer | – | window in days (default 30, 0 = all time) |
| source | string | – | drill into one source, e.g. telegram / cron / heartbeat / subagent |
No output schema declared.
No examples provided.
burn_commits ~109
What each git commit cost, in weighted tokens: sessions joined to the repositories they ran in (read-only git log). Costliest commits, median per repository. Returns JSON.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | – | hermes | openclaw | claude-code (default: first detected) |
| days | integer | – | window in days (default 30, 0 = all time) |
| source | string | – | drill into one source, e.g. telegram / cron / heartbeat / subagent |
No output schema declared.
No examples provided.
burn_context ~140
The price of long contexts on this machine: share of the usage window spent at each context size, what a /clear at 100k/150k/200k/300k would have saved, the longest sessions, usage by effort level, and what each skill costs per load (measured from context growth). Returns JSON.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | – | hermes | openclaw | claude-code (default: first detected) |
| days | integer | – | window in days (default 30, 0 = all time) |
| source | string | – | drill into one source, e.g. telegram / cron / heartbeat / subagent |
No output schema declared.
No examples provided.
burn_limits ~139
For subscription plans, where the invoice is fixed and what runs out is the usage window: how full the peak rolling 5-hour window got, how it compares with a typical one, what filled it (model, source, cache reads vs output). Weighted by published price ratios; no provider limit formula is assumed. Returns JSON.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | – | hermes | openclaw | claude-code (default: first detected) |
| days | integer | – | window in days (default 30, 0 = all time) |
| source | string | – | drill into one source, e.g. telegram / cron / heartbeat / subagent |
No output schema declared.
No examples provided.
burn_report ~117
Where this machine's AI agent burns money: totals, monthly pace, breakdown by source (cron/heartbeat/gateways/subagents/cli), models, overnight window, fixed overhead per call, recommendations. Returns JSON.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | – | hermes | openclaw | claude-code (default: first detected) |
| days | integer | – | window in days (default 30, 0 = all time) |
| source | string | – | drill into one source, e.g. telegram / cron / heartbeat / subagent |
No output schema declared.
No examples provided.
burn_why ~117
Behavioral forensics from the agent's own records: functions called (with error counts), re-read loops, retry storms, idle heartbeats, money burned in failed runs, plus what-to-change observations. Returns JSON.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | – | hermes | openclaw | claude-code (default: first detected) |
| days | integer | – | window in days (default 30, 0 = all time) |
| source | string | – | drill into one source, e.g. telegram / cron / heartbeat / subagent |
No output schema declared.
No examples provided.
What is the agentburn MCP server?
agentburn is an MCP server listed in the public MCP registry as io.github.Socialpranker/agentburn. Local profiler: which usage window took you out, and where your agent's money goes. This page covers its PyPI package (agentburn).
Is the agentburn MCP server safe to use?
agentburn scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the agentburn MCP server expose?
agentburn exposes 6 tools: burn_report, burn_why, burn_limits, burn_context, burn_commits, burn_card. Their descriptions and schemas cost roughly 710 tokens of context every time the server is loaded.
Is the agentburn MCP server still maintained?
agentburn is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the agentburn MCP server under?
agentburn declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.