Should my agent depend on the MCP server io.corpusiq/multi-source-mcp?

Verdict: allow — stale-rich-solo — safe to depend on As of 2026-08-15T11:28:18Z: a dated observation with receipts, not a warranty.

CorpusIQ

io.corpusiq/multi-source-mcp

Authenticated, user-scoped MCP connectors for 30+ business systems.

— the operator's own registry description reported

Publisher io.corpusiq · first seen 2026-08-12 · endpoint https://mcp2.corpusiq.io/mcp

allow

verdict

stale-rich-solo

cluster

ok_tools

answers

tools served

Dependency rating derived

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

Cluster stale-rich-solo · distinctiveness 0.691 (unusual). Every figure is a percentile or class within the 11,094-server census — see the whole spectrum.

Reach — can an agent get to it?

answersalive_tools

latency318 ms

vs populationtypical

protocolbehind

authopen

Use — can it use it?

tools77

vs populationhigh

capabilities3

harnessA

Trust — can it rely on it?

identitysolo

servers on its host1

verifiabilityunassessed

duplicate inventoryno

drift events0

answers true0/0 agree

🔏 Signed receipt rr_71b0db29341de0e1fa63a07c · 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

activecampaign_connector ahrefs_connector airtable_connector amazon_seller_connector axonaut_connector bing_webmaster_connector calendar_connector calendly_connector callrail_connector canonical_connector canonical_context_get canonical_decisions_add canonical_decisions_list canonical_facts_get canonical_facts_list canonical_facts_set canonical_pending_cancel canonical_pending_commit close_connector constantcontact_connector crm_connector cross_source_ads_connector cross_source_email_connector database_connector disable_connector drive_connector ebay_connector email_connector enable_connector featured_cash_recovery_engine featured_competitive_intelligence_brief featured_executive_summary_writer featured_sales_call_prep_brief featured_seo_audit ga4_connector get_connector_status get_my_usage_stats get_user_statistics google_ads_connector gunbroker_connector invoke_skill klaviyo_connector linkedin_ads_connector list_runbooks list_skills logout_all mailchimp_connector meta_ads_connector metric_spec_drift_report metric_spec_get metric_spec_list metric_spec_remove metric_spec_resolve metric_spec_set monday_connector notion_connector odoo_connector podium_connector posthog_connector postscript_connector quickbooks_connector reset_connector_token resolve_connector run_runbook salesforce_connector search_console_connector select_runbook semrush_connector shopline_connector slack_connector stripe_connector tiktok_connector truth_sources_list truth_sources_register truth_sources_remove web_fetch_connector youtube_connector

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	77/77	✓
has a description	77/77	✓
description is substantive	77/77	✓
parameters are typed	77/77	✓
parameters are described	73/77	73/77

77 of 77 tools graded · 77 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 · 2 unverifiable.

claim class	key	verdict	primary source
tariff-duty	6109.10.00	unverifiable	us-hts
tariff-duty	8471.30.01	unverifiable	us-hts

Protocol conformance observed

2025-03-26

protocol version

—

session model

1.0.0

server version multi-source-mcp

Capabilities: prompts 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)

date	type	what changed
2026-08-12	outcome	first probe: ok_tools

raw probe records

probed (UTC)	outcome	http	ms	protocol
2026-08-14T19:58:51Z	ok_tools	200	318	2025-03-26
2026-08-12T05:34:05Z	ok_tools	200	514	2025-03-26

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/io.corpusiq/multi-source-mcp.svg)](https://robinsaige.com/s/io.corpusiq/multi-source-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