Should my agent depend on the MCP server dev.mcphost/mcphost?

Verdict: allow — rich-solo — safe to depend on As of 2026-09-13T06:22:43Z: a dated observation with receipts, not a warranty.

mcphost

dev.mcphost/mcphost

Host your MCP tool over streamable HTTP in one command.

— the operator's own registry description reported

Publisher dev.mcphost · first seen 2026-09-07 · endpoint https://mcphost.dev/mcp

allow

verdict

rich-solo

cluster

ok_tools

answers

tools served

Dependency rating derived

allow
allow — alive & usable · action ● · V n/a

allow — because answers ●, 51 tools legible (band A) ●, no confirmed drift in 1 probes ●; not yet checked: truth (0 runs)

Cluster rich-solo · distinctiveness 0.562 (moderate). Every figure is a percentile or class within the 19,148-server census — see the whole spectrum.

Does it answer? Q1 · observed

answersalive_tools

latency339 ms

vs populationtypical

protocolcurrent

authopen

Can it be used? Q4 · observed

tools51

vs populationhigh

capabilities1

harnessA

Did it hold when checked? Q3–Q4 · derived

identitysolo

servers on its host1

verifiabilityunassessed

duplicate inventoryno

drift events0

answers trueno primary

🔏 Signed receipt rr_01e84009a6f1a37971630da1 · 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.

Q1Does it answer?alive & usable — 1 probes ●evidence ↓

Q2What is it?action ● evidence ↓

Q3Can it be checked?V n/a for this kind ◐evidence ↓

Q4Did it hold?harness A · truth not yet run · no drift ●evidence ↓

Q5What company does it keep?rich-solo · 1 on its host (context, not verdict) ◐evidence ↓

● observed · ◐ derived · ○ reported — the verdict synthesizes Q1–Q4; Q5 is context. Methodology →

History observed

Every probe we made, oldest → newest (1 shown, 2026-09-13 → 2026-09-13). 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)

date	type	what changed
2026-09-13	outcome	first probe: ok_tools

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. Classification evidence: classified from tool names/descriptions/annotations WE OBSERVED. What checking applies to each kind (the full methodology →):

nature	tools	meaning	what checking applies
action	34	changes the world	no true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
unclassified	10	not classifiable from its text	Tier-1 only until its tools describe themselves
retrieval-public	7	serves public facts	truth-checkable against a public source — the V-ladder applies in full

Tools last seen observed

billing.checkout billing.plans billing.status host.bridge_test host.catalog.get host.catalog.search host.group.add host.group.create host.group.list host.group.remove host.key_rotate host.quickstart host.redeem host.registry_publish host.runs.cancel host.runs.get host.runs.list host.runs.purge host.runs.wait host.secret_list host.secret_set host.state.delete host.state.delete_rows host.state.get host.state.insert host.state.list host.state.query host.state.set host.state.table_create host.state.table_drop host.tool_call host.tool_list host.tool_logs host.tool_publish host.tool_remove host.tool_run host.tool_share host.tool_test host.tool_unshare host.trigger.fire host.trigger.get host.trigger.list host.trigger.pause host.trigger.remove host.trigger.replay host.trigger.resume host.trigger.set host.trigger.test host.usage host.whoami signup

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 A — an agent can pick and call these reliably.

legibility check	tools passing	ok
name is clear & specific	51/51	✓
has a description	51/51	✓
description is substantive	49/51	49/51
parameters are typed	48/51	48/51
parameters are described	51/51	✓

51 of 51 tools graded · 51 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

2025-06-18

protocol version

—

session model

3.3.0

server version rmcp

Capabilities: tools

Drift observed

No confirmed drift on record. Baseline set 2026-09-13; changes appear here after human review.

raw probe records

probed (UTC)	outcome	http	ms	protocol
2026-09-13T06:14:04Z	ok_tools	200	339	2025-06-18

Watch or embed this verdict

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/dev.mcphost/mcphost.svg)](https://robinsaige.com/s/dev.mcphost/mcphost)

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

Operator of this server? Everything we hold about it is on this page — free, no account, for anyone. Wrong attribution, stale probe, misclassification? Dispute this record →