Robin Saige we check the tools AI agents call

Tap

io.github.LeonTing1010/tap

Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay.

— the operator's own registry description reported

Publisher io.github.LeonTing1010 · first seen 2026-08-12 · endpoint https://mcp.taprun.dev/mcp

allow
verdict
stale-thin-solo
cluster
ok_tools
answers
4
tools served

Dependency rating derived

allow — stale-thin-solo — safe to depend on

Cluster stale-thin-solo · distinctiveness 0.249 (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
latency139 ms
vs populationtypical
protocolstale
authopen
Use — can it use it?
tools4
vs populationmid
capabilities2
harnessB
Trust — can it rely on it?
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_8d4b885ea3c7ecc7cc4ccc3c · 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.

Tools last seen

capture mark run verify

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 & specific3/43/4
has a description4/4
description is substantive4/4
parameters are typed4/4
parameters are described1/41/4

4 of 4 tools graded · 4 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

Not in the Tier-2 trade lane, or not yet checked. Tier-2 re-derives a server's answers against published primary sources — see truth checks.

Protocol conformance observed

2024-11-05
protocol version
session model
0.20.4-edge
server version tap

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
2026-08-14T19:59:06Zok_tools2001392024-11-05
2026-08-12T05:34:21Zok_tools2001082024-11-05

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.LeonTing1010/tap.svg)](https://robinsaige.com/s/io.github.LeonTing1010/tap)

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