AgentBill
PYPI · AGENTBILL-MCP · 2 COMPONENTS
One spend ceiling per agent job, as MCP tools. Bound to a task_ref you pass, not a calendar month.
Available components
Last scanned (23 hours ago)
Scores higher than 68% of PyPI servers
Category Finance and Payments
Recent critical change
GHSA-6q48-6c7w-9gw2 affects this package (21 Oct 2026). See the changelog before you install this server.
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 hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 0 of 28 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency23
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- 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 56 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability64
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 624 tokens (~312/item across 2 items; 2 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage67
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 3 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
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
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.
- 19 Nov 26 0
- Stability: 0.97 → pass security
- 18 Nov 26 0
- Stability: pass → 0.97 functional
- 12 Nov 26 0
- Stability: 0.97 → pass security
- 10 Nov 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 Nov 26 −1
- Stability: pass → 0.87 functional
- 2 Nov 26 0
- Stability: 0.97 → pass security
- 1 Nov 26 0
- Stability: pass → 0.97 functional
- 25 Oct 26 0
- Stability: 0.97 → pass security
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 21 Nov 2026 · Analysed pypi/agentbill-mcp@0.3.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | Known build tool | hatchling.build |
Background: Why install scripts are a supply-chain risk →
Dependencies 28 packages
| Packages resolved | 28 |
|---|---|
| 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 →
preflight ~408
Check if an agent is allowed to run before starting work. Call this at the start of every agent invocation. Returns approved=True when the run has budget. Returns approved=False with a reason when preflight refused the call (budget_exhausted, ceiling_exceeded, free_tier_exceeded, task_ceiling_exceeded). Nothing is stopped by this server; the host decides. A unit is an integer you define and pass. AgentBill reserves the number you send and never converts those units into money, so the ceiling is only as tight as your estimate. The common convention is 1 unit = 1 cent. (Model calls recorded through the Python or Node SDK's wrap() are counted in tokens instead.) Args: agent_id: Identifier for this agent or task type (e.g. "research_agent"). customer_id: Your internal customer identifier. Defaults to "default". estimated_units: How many units you expect this run to consume. This is the number reserved against every budget below. ceiling: Max units allowed per single call. The call is refused if estimated_units exceeds this. task_ref: Groups many calls under one cross-call budget, so one job spanning several providers and tools shares a single ceiling. Pass the same task_ref on every call in the job. task_ceiling: Total units the whole task may spend. Required on the first preflight of a new task_ref, or open the job first in the console; not applied on later calls. idempotency_key: Makes a retried preflight safe. Without it a retry reserves a second time. Same key, same decision, one reservation.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| ceiling | – | – | – |
| customer_id | string | – | – |
| estimated_units | integer | – | – |
| idempotency_key | – | – | – |
| task_ceiling | – | – | – |
| task_ref | – | – | – |
No output schema declared.
No examples provided.
record_event ~145
Record a billable event after agent work is complete. Call this once per unit of work completed. Safe to call from retried or parallel workflows, duplicate submissions are ignored automatically. Args: agent_id: Identifier for this agent or task type. Appears in the dashboard. units: Number of billable units this event represents. Default is 1. customer_id: Your internal customer identifier. Defaults to "default". metadata: Optional key-value pairs stored with the event (e.g. model name, latency).
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| customer_id | string | – | – |
| metadata | – | – | – |
| units | integer | – | – |
No output schema declared.
No examples provided.
How do I install the AgentBill MCP server?
AgentBill runs locally as a PyPI package, launched with uvx agentbill-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · agentbill-mcp
claude mcp add marketinglior-pixel-agentbill-mcp -- uvx agentbill-mcp
What is the AgentBill MCP server?
AgentBill is an MCP server listed in the public MCP registry as io.github.marketinglior-pixel/agentbill-mcp. One spend ceiling per agent job, as MCP tools. Bound to a task_ref you pass, not a calendar month. This page covers its PyPI package (agentbill-mcp).
Is the AgentBill MCP server safe to use?
AgentBill scores 75 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 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 AgentBill MCP server expose?
AgentBill exposes 2 tools: preflight, record_event. Their descriptions and schemas cost roughly 553 tokens of context every time the server is loaded.
Is the AgentBill MCP server still maintained?
AgentBill is still listed as active in the MCP registry. We last reached this channel on 21 November 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 AgentBill MCP server under?
AgentBill declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the AgentBill MCP server?
VerifyMCP ran 16 checks on AgentBill, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.