Robin Saige we check the tools AI agents call

Saber

app.saber.mcp/saber

Sales intelligence — research companies, qualify prospects, and find contacts.

— the operator's own registry description reported

Publisher app.saber.mcp · first seen 2026-08-12 · endpoint https://mcp.saber.app/mcp

allow
verdict
rich-solo
cluster
ok_tools
answers
119
tools served

Dependency rating derived

allow — rich-solo — safe to depend on

Cluster rich-solo · distinctiveness 0.602 (unusual). 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
latency156 ms
vs populationtypical
protocolcurrent
authopen
Use — can it use it?
tools119
vs populationhigh
capabilities3
harnessB
Trust — can it rely on it?
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_11c2843ccb3f47c882d25d85 · 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

companies-enrich_custom companies-enrich_custom_batch companies-enrich_firmographics companies-enrich_funding companies-enrich_mna companies-enrich_open_jobs companies-enrich_tech_stack companies-generate_summary companies-list_summaries company_lists-count_preview company_lists-create company_lists-delete company_lists-export company_lists-get company_lists-get_companies company_lists-import company_lists-list company_lists-search company_lists-update company_signals-create company_signals-create_batch company_signals-get company_signals-list company_signals-subscription_logs connectors-list contact_lists-create contact_lists-delete contact_lists-get contact_lists-get_contacts contact_lists-list contact_lists-update contacts-create_research contacts-create_signal contacts-enrich_custom contacts-enrich_work_email contacts-get_research contacts-get_signal contacts-list_signals contacts-search credits-get_balance enrichment_runs-get enrichment_runs-list enrichment_templates-create enrichment_templates-delete enrichment_templates-get enrichment_templates-list enrichment_templates-update enrichment_types-list findEmail findEmailBatchGet findEmailBatchSubmit getContactResearchByExternalID market_signals-create_subscription market_signals-delete_subscription market_signals-get_subscription market_signals-list_signals market_signals-list_subscriptions market_signals-pause_subscription market_signals-resume_subscription market_signals-trigger_subscription market_signals-update_subscription monitors-create monitors-create_action monitors-delete monitors-delete_action monitors-get monitors-get_action monitors-list monitors-list_actions monitors-list_signals monitors-pause monitors-pause_action monitors-resume monitors-resume_action monitors-trigger monitors-update monitors-update_action organisation-get organisation-update scoring-assignment-bulk-create scoring-assignment-create scoring-assignment-delete scoring-assignment-list scoring-compute scoring-profile-create scoring-profile-delete scoring-profile-get scoring-profile-list scoring-profile-update scoring-rule-delete scoring-rule-list scoring-rule-upsert scoring-scores-get signal_subscriptions-create signal_subscriptions-get signal_subscriptions-list signal_subscriptions-start signal_subscriptions-stop signal_subscriptions-trigger signal_subscriptions-update signal_summaries-generate signal_summaries-list signal_templates-create signal_templates-delete signal_templates-get signal_templates-list signal_templates-update signals-firmographics signals-funding signals-mna signals-open_jobs signals-tech subscription_actions-create subscription_actions-delete subscription_actions-get subscription_actions-list subscription_actions-pause subscription_actions-unpause subscription_actions-update

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 & specific119/119
has a description119/119
description is substantive52/11952/119
parameters are typed118/119118/119
parameters are described96/11996/119

119 of 119 tools graded · 119 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
0.1.0
server version saber

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 (2 events)
datetypewhat changed
2026-08-14inventorytools 84 → 119
2026-08-12outcomefirst probe: ok_tools
raw probe records
probed (UTC) outcomehttpmsprotocol
2026-08-14T19:57:46Zok_tools2001562025-06-18
2026-08-12T05:33:03Zok_tools2002062025-06-18

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/app.saber.mcp/saber.svg)](https://robinsaige.com/s/app.saber.mcp/saber)

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