Skip to content
Agentmart
Submit a tool

Plzebo

Cost-parity bench for agent loops: $/success and time across model mixes, with verifiable receipts.

Connector by wkoverfield · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/wkoverfield-plzebo

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Cost-parity bench for agent loops: $/success and time across model mixes, with verifiable receipts.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
3 read · 0 write · 0 delete · 1 not yet classified
Secrets
2 (API keys, tokens or passwords)
Install scripts
Not scanned yet
Runs as
Node.js package

Tools by what they do 4

Read from the source code; the running server may list different tools.

Read 3 · Look things up without changing anything.

  • measure_extend
  • measure_result
  • measure_status

Not yet classified 1 · We could not tell from the name and description.

  • measure_start

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • ANTHROPIC_API_KEY
  • OPENAI_API_KEY

Tools (4)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • measure_extend

    Extend a completed measurement to a larger K, reusing its trials. First call ({receipt_path, to_k, budget_usd}): verifies the base receipt, returns an estimate and a one-time confirm token, spends nothing. Second call ({job_id, confirm_token}): runs the added trials. A receipt may be extended only once; the interim look is disclosed.

  • measure_result

    Final verdict of a completed measure job: receipt path, per-arm summaries, comparisons with CIs and do-not-claim lists.

  • measure_start

    Start a plzebo measurement. First call (spec, no confirm_token): validates, returns a cost estimate and a one-time confirm token, spends nothing. Second call ({job_id, confirm_token}): launches the trials in the background, spending real tokens up to budget_usd.

  • measure_status

    Progress of a measure job: state, trials done, metered spend. Pass cancel:true to cancel (a trial in flight completes first).

Signals

Stars
0
Forks
0
Open issues
0
Last commit
Aug 14, 2026 (2 months ago)
Last release
Aug 14, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.wkoverfield/plzebo
Version
0.2.0
Auth
API key
Packages
npm plzebo
License
MIT
Repository
github.com/wkoverfield/plzebo
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql

More from wkoverfield

Cite this page

Plzebo MCP server. Agent Mart. https://agentmart.dev/connectors/wkoverfield-plzebo (last updated 2026-10-24)