Robin Saige we check the tools AI agents call

Algenta MCP Server

io.github.thyn-ai/algenta

Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.

— the operator's own registry description reported

Publisher io.github.thyn-ai · first seen 2026-08-12 · endpoint https://api.algenta.ai/mcp

allow
verdict
rich-solo
cluster
ok_tools
answers
140
tools served

Dependency rating derived

allow
allow — alive & usable · action ● · V n/a
allow — because answers ●, 140 tools legible (band A) ●, no confirmed drift in 2 probes ●; not yet checked: truth (3 attempts unverifiable, 0 disagreements)

Cluster rich-solo · distinctiveness 0.48 (moderate). Every figure is a percentile or class within the 11,094-server censussee the whole spectrum.

Does it answer? Q1 · observed
answersalive_tools
latency103 ms
vs populationtypical
protocolcurrent
authopen
Can it be used? Q4 · observed
tools140
vs populationhigh
capabilities2
harnessA
Did it hold when checked? Q3–Q4 · derived
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers true0/0 agree

🔏 Signed receipt rr_b886a4d250e037517da44ab5 · 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 — 2 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 (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

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 →):

naturetoolsmeaning what checking applies
action70changes the worldno true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
retrieval-public41serves public factstruth-checkable against a public source — the V-ladder applies in full
unclassified24not classifiable from its textTier-1 only until its tools describe themselves
predictive2claims about the futurescoreable only in retrospect — the archive scores yesterday's predictions against today's outcome
computational1deterministic transformsself-checkable by re-computation and known-answer tests
generative1creates contentno answer key exists; disclosure + stability checks, never truth verdicts
orchestration1routes other toolsidentity + fronted-service disclosure checks (gateway vs costume)

Tools last seen observed

apply_repository approve_agent_run batch browse_connector cancel_agent_run cancel_job chat_completions compare connect_data count_tokens create_agent_run create_api_key create_billing_checkout create_billing_portal create_capability_binding create_connector create_deployment create_repository_decision_plan create_repository_snapshot delete_connector delete_decision delete_deployment delete_trigger disable_skill disconnect_data discover_capability_binding embedding_similarity embeddings enable_skill execute_capability execute_decision execute_runtime_library fire_trigger get_agent_run get_agent_run_checkpoints get_agent_run_events get_agent_run_mission_events get_agent_run_telemetry get_analytics get_audit_log_artifacts get_audit_logs get_billing_info get_capability get_connector get_contract get_data_schema get_data_summary get_dataset_status get_decision get_deployment get_deployment_cost get_execution_policy get_job_result get_job_status get_limits get_me get_repository_intelligence_capabilities get_repository_snapshot get_run get_runtime_benchmarks get_runtime_manifest get_runtime_modules get_runtime_release_validation get_source_schema get_usage ingest_data ingest_metering_events invite_team_member list_agent_runs list_api_keys list_capabilities list_capability_bindings list_capability_providers list_connectors list_data list_datasets list_decisions list_deployment_regions list_devices list_distributions list_execution_policy_snapshots list_jobs list_models list_runs list_runtime_libraries list_skills list_sources list_team_members list_templates list_triggers log_decision onboard_dataset pause_trigger plan_decision poll_job preview_browse_connector preview_test_connector product_agent_run product_decision product_forecast product_optimize product_retrieve query_agent_run_checkpoints query_agent_run_mission_events query_agent_run_telemetry query_batch query_data query_repository_graph query_sql_report recommend record_outcome refresh_credits refresh_data register_source register_trigger remove_team_member rerank resolve_artifact_bridge responses resume_agent_run retrain_dataset revoke_api_key revoke_device route_capabilities run_repository_fix run_repository_pipeline score simulate simulate_repository simulate_repository_patch submit_job test_capability_binding test_connector test_webhook_delivery tokenize triage_repository update_connector update_execution_policy update_me update_team_member_role

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 checktools passingok
name is clear & specific140/140
has a description140/140
description is substantive133/140133/140
parameters are typed139/140139/140
parameters are described58/14058/140

140 of 140 tools graded · 140 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 yet confirmed — 3 attempt(s) currently unverifiable (rate limits, walls, or unmappable schemas — never counted against the server) · 0 disagreements.

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
1.0.4
server version algenta-mcp

Capabilities: experimental tools

Drift observed

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

raw probe records
probed (UTC) outcomehttpmsprotocol
2026-08-14T20:00:16Zok_tools2001032025-06-18
2026-08-12T05:35:28Zok_tools200922025-06-18

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.thyn-ai/algenta.svg)](https://robinsaige.com/s/io.github.thyn-ai/algenta)

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