Robin Saige we check the tools AI agents call

Workopia — Job Search

io.github.workopia/workopia-mcp

Search 6.3M+ live jobs from companies' own career pages, plus resume tailoring & cover letters.

— the operator's own registry description reported

Publisher io.github.workopia · first seen 2026-08-12 · endpoint https://workopia.io/api/mcp-jobs

allow
verdict
mid-solo
cluster
ok_tools
answers
5
tools served

Dependency rating derived

allow — mid-solo — safe to depend on

Cluster mid-solo · distinctiveness 0.171 (typical). Every figure is a percentile or class within the 11,094-server censussee the whole spectrum.

Reach — can an agent get to it?
answersalive_tools
latency196 ms
vs populationtypical
protocolcurrent
authopen
Use — can it use it?
tools5
vs populationmid
capabilities2
harnessB
Trust — can it rely on it?
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers true0/0 agree

🔏 Signed receipt rr_d3443ad29dd86e7ceb15325a · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.

What kind of tools these are derived

Verification only means something relative to a tool's NATURE — an email-sender has no "true answer", a generator has no answer key. This server's 5 tools, classified, with what checking applies to each kind (the full methodology →):

naturetoolsmeaning what checking applies
action3changes the worldno true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
generative1creates contentno answer key exists; disclosure + stability checks, never truth verdicts
retrieval-public1serves public factstruth-checkable against a public source — the V-ladder applies in full

Tools last seen

cover_letter_tool dashboard_tool job_detail_tool job_tool tailor_resume_tool

Harness readiness observed

Can an agent's harness pick this tool and call it correctly? Graded on the three things an agent reads — name, description, typed parameters. Band B — usable, with rough edges.

legibility checktools passingok
name is clear & specific5/5
has a description5/5
description is substantive5/5
parameters are typed5/5
parameters are described0/50/5

5 of 5 tools graded · 5 with a captured input schema. RS-008, Tier-1 — no domain knowledge, applies to any tool. “Alive” is not the same as “usable”.

Truth checks observed

0/0 answers agree with the published primary source · 3 unverifiable.

claim classkeyverdictprimary source
tariff-duty0901.21.00unverifiableus-hts
tariff-duty6109.10.00unverifiableus-hts
tariff-duty8471.30.01unverifiableus-hts

Protocol conformance observed

2025-06-18
protocol version
session model
2.0.0
server version Workopia

Capabilities: resources tools

Drift

No confirmed drift on record. Baseline set 2026-08-14; changes appear here after human review.

History observed

Every probe we made, oldest → newest (2 shown, 2026-08-12 → 2026-08-14). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.

changelog (1 events)
datetypewhat changed
2026-08-12outcomefirst probe: ok_tools
raw probe records
probed (UTC) outcomehttpmsprotocol
2026-08-14T20:00:20Zok_tools2001962025-06-18
2026-08-12T05:35:32Zok_tools20039792025-06-18

Watch or embed this verdict

verdict badge

Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:

[![Robin Saige verdict](https://robinsaige.com/badge/io.github.workopia/workopia-mcp.svg)](https://robinsaige.com/s/io.github.workopia/workopia-mcp)

Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.

← overview