Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Algenta MCP Server

PYPI · ALGENTA-MCP · 2 COMPONENTS · SCANNED SEP 21

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

+32 this week 63 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 1 of 38 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency35
Schema Quality & AI Usability64
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 8616 tokens (~61/item across 140 items; 140 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage76
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 29% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 15 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "disconnect_data" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 140 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

Install

How do I install the Algenta MCP Server server?

Algenta MCP Server runs locally as a PyPI package, launched with uvx algenta-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · algenta-mcp

# add to Claude Code
claude mcp add thyn-ai-algenta -- uvx algenta-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "thyn-ai-algenta": {
      "command": "uvx",
      "args": [
        "algenta-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "thyn-ai-algenta": {
      "command": "uvx",
      "args": [
        "algenta-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add thyn-ai-algenta -- uvx algenta-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "thyn-ai-algenta": {
      "type": "local",
      "command": [
        "uvx",
        "algenta-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add thyn-ai-algenta --command uvx --arg algenta-mcp
# ~/.hermes/config.yaml
mcp_servers:
  thyn-ai-algenta:
    command: "uvx"
    args: ["algenta-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "thyn-ai-algenta": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "algenta-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add thyn-ai-algenta -t stdio -c uvx -a algenta-mcp
// mcp.json
{
  "mcpServers": {
    "thyn-ai-algenta": {
      "command": "uvx",
      "args": [
        "algenta-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +15
    • Malware scan: unverified → pass security
    • Security disclosure: unverified → pass functional
  • 19 Sept 26 +17
    • Malware scan: pass → unverified security
    • Injection markers: unverified → pass security
    • Source repository: fail → pass security
    • First check of Judged manipulation: pass security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • Tool coverage: unverified → 100 functional
    • MCP protocol: unverified → pass functional
    • First check of Tool coverage: 29 functional
    • First check of Schema quality: fail functional
    • First check of Destructive annotations: 0 functional
    • First check of Schema quality: pass functional
    • First check of Schema quality: good functional
    • Package version: 1.0.4 → 1.0.14 functional
    • Package version: 1.0.4 → 1.0.13 functional
  • 26 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 4 Aug 26 0
    • Known CVEs: unverified → pass security
    • Dependency health: unverified → 0.99 functional
  • 2 Aug 26 0
    • Provenance: unverified → fail security
    • Install scripts: unverified → pass security
    • Malware scan: unverified → pass security
    • Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. security
    • The scripts that run when this package is installed changed: build_backend security
    • License: unverified → fail functional
    • Maintenance: unverified → pass functional
    • Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. functional
    • Capabilities: Protocol version not yet verified: we do not have a sandbox capture of the MCP handshake this version of the package performs yet. functional
    • Tool coverage: Tool coverage not yet verified: we do not have a sandbox capture of the tool definitions this version of the package serves yet. functional
  • 31 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 0
    • Install scripts: pass → unverified security
    • Provenance: fail → unverified security
    • Known CVEs: pass → unverified security
    • The scripts that run when this package is installed changed: build_backend security
    • Dependency health: 0.99 → unverified functional
    • License: fail → unverified functional
    • Maintenance: pass → unverified functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Sept 2026 · Analysed pypi/algenta-mcp@1.0.14

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted setuptools.build_meta

Background: Why install scripts are a supply-chain risk →

Dependencies 38 packages
Packages resolved 38
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 140 exposed · ~8,616 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
product_optimize ~57

Run the simple product optimization helper and return the best variable values.

NameTypeReqDescription
constraintsarray
enginestring
iterationsinteger
objectivestringyes
variablesarrayyes

No output schema declared.

No examples provided.

product_retrieve ~64

Run the simple product retrieval helper over caller-supplied documents or a collection id.

NameTypeReqDescription
collection_idstring
documentsarray
querystringyes
rerankboolean
top_kinteger

No output schema declared.

No examples provided.

query_agent_run_checkpoints ~83

Query persisted checkpoints across Algenta agent runs.

NameTypeReqDescription
checkpoint_idstring
limitinteger
pageinteger
policy_snapshot_idstring
request_hashstring
run_idstring
schema_snapshot_idstring
statusstring

No output schema declared.

No examples provided.

query_agent_run_mission_events ~87

Query canonical mission-event records across persisted Algenta agent runs.

NameTypeReqDescription
event_typestring
limitinteger
pageinteger
policy_snapshot_idstring
request_hashstring
run_idstring
schema_snapshot_idstring
statusstring

No output schema declared.

No examples provided.

query_agent_run_telemetry ~94

Query runtime telemetry batches across persisted Algenta agent runs.

NameTypeReqDescription
limitinteger
module_namestring
pageinteger
policy_snapshot_idstring
request_hashstring
run_idstring
schema_snapshot_idstring
statusstring
telemetry_kindstring

No output schema declared.

No examples provided.

query_batch ~89

Execute several governed exact queries in one API call. Use this for multi-metric prompts after choosing a dataset with list_data and get_data_summary. Each item reuses the same structured query contract as query_data; defaults may provide shared dataset_id, filter, limit, and order.

NameTypeReqDescription
defaultsobjectOptional shared exact-query fields applied to each item before execution.
queriesarrayyes

No output schema declared.

No examples provided.

query_data ~332

Execute a structured query against connected data sources. Convert the user's question to a structured intent and call this tool — do NOT try to write SQL or parse column names yourself. The engine resolves column meaning from mathematical relationships and statistical structure only. It works on any dataset without configuration. The governed filter shape is a record-predicate contract over normalized rows, not a SQL predicate language, so it also applies to Redis and other non-SQL sources. Structural roles (use in metric.role): - derived_measure: the main financial/operational aggregate (revenue, spend, value) - base_measure: counts, quantities, discrete amounts - unit_measure: per-unit prices, rates - ratio: percentages, margins, fill rates (0-1 range) - metric: let the engine pick the best numeric column If clarification_required is true, or if confidence < 0.85, check the candidates list and ask the user to clarify. Never fabricate column names or SQL.

NameTypeReqDescription
aggregationstringHow to aggregate the metric column.
dataset_idstringPreferred path. dataset_id returned by connect_data or list_data.
filterobject
group_byarrayDimension words from the user's question (e.g. ['customer', 'region']). The engine finds the best matching column.
limitintegerTop-N limit. Use for 'top 5 customers' type questions.
metricobjectWhat to measure.
orderstring
sourcesarrayData sources to query. Usually omitted when dataset_id is provided.

No output schema declared.

No examples provided.

query_repository_graph ~91

Query one persisted repository snapshot for dependency, dependent, and change-risk graph edges.

NameTypeReqDescription
directionstring
file_pathstring
max_depthinteger
max_nodesinteger
repository_idstringyes
snapshot_idstring
symbol_namestring
workspace_evidence_bundle_refstring

No output schema declared.

No examples provided.

query_sql_report ~99

Execute a constrained read-only SQL rowset query over authorized datasets. Use this only for wide reports that do not fit the governed exact-query surface. SQL must be a single SELECT/WITH statement over the provided dataset aliases.

NameTypeReqDescription
max_rowsintegerOptional row cap, up to the API maximum.
sourcesarrayyesAuthorized datasets made available to the SQL report.
sqlstringyesSingle read-only SELECT or WITH statement.

No output schema declared.

No examples provided.

recommend ~57

Compare multiple named actions/options and get a ranked recommendation. Use when you need to choose between two or more alternatives with uncertainty.

NameTypeReqDescription
actionsarrayyesList of options to compare (minimum 2)
n_simulationsinteger

No output schema declared.

No examples provided.

record_outcome ~97

Close the feedback loop: record what actually happened after a decision was made. Sets actual_outcome and computes outcome_delta = actual - expected. Over time this data measures prediction accuracy and reveals systematic biases.

NameTypeReqDescription
actual_outcomenumberyesThe observed real-world outcome value.
decision_idstringyesDecision ID from log_decision or list_decisions.
outcome_notesstringOptional explanation of what happened and why.

No output schema declared.

No examples provided.

refresh_credits ~47

Issue a compatibility credit batch for a quota-governed managed runtime.

NameTypeReqDescription
billing_periodstringyes
credits_usedinteger
device_idstringyes

No output schema declared.

No examples provided.

refresh_data ~37

Refresh a saved dataset from its original database/API/object-store origin.

NameTypeReqDescription
dataset_idstringyesDataset ID from connect_data or list_data.

No output schema declared.

No examples provided.

register_source ~132

Advanced tool. Register a data source and get full schema profiling + join detection. Profiles every column (type, cardinality, fill rate, distribution). Detects formula relationships (A×B≈C) within the source. Detects join keys to every already-registered source automatically. After registration the source is queryable by name via query_data. Safe to call multiple times — re-registration is a no-op if data is unchanged.

NameTypeReqDescription
descriptionstringOptional human description of this source.
sourceobjectyesData source definition. Provide exactly one of: records, csv, json_str, url.

No output schema declared.

No examples provided.

register_trigger ~193

Register a real-time trigger that watches a data source for a threshold condition. When the condition is met, the engine auto-runs the simulation template and optionally fires a webhook. Examples: 'alert me when monthly revenue drops below $80k', 'simulate expansion if Downtown revenue exceeds $200k'.

NameTypeReqDescription
auto_executebooleanWhen true, automatically dispatch the decision plan to execution_webhook_url after the trigger fires.
conditionobjectyesThreshold condition to watch.
descriptionstringHuman-readable description of what this trigger monitors.
execution_webhook_urlstringOptional HTTPS URL to POST the DecisionPlan execution payload to when auto_execute is enabled.
namestringyesHuman-readable trigger name.
simulation_templateobjectyesSimulateRequest-compatible payload to run when trigger fires.
webhook_urlstringOptional HTTPS URL to POST results to when the trigger fires.

No output schema declared.

No examples provided.

remove_team_member ~29

Remove one team member from the current organization by user id.

NameTypeReqDescription
user_idstringyes

No output schema declared.

No examples provided.

rerank ~50

Rerank caller-supplied document embeddings deterministically.

NameTypeReqDescription
documentsarrayyes
modelstring
query_embeddingarrayyes
top_ninteger

No output schema declared.

No examples provided.

resolve_artifact_bridge ~71

Resolve a Hugging Face artifact path through the Algenta compatibility-ring artifact bridge. Defaults to cache-only lookup and never downloads unless local_files_only=false.

NameTypeReqDescription
filenamestringyes
local_files_onlyboolean
repo_idstringyes
revisionstring

No output schema declared.

No examples provided.

responses ~42

Run the unified Algenta utility response surface over deterministic tokenization or lexical embeddings.

NameTypeReqDescription
dimensionsinteger
inputyes
modelstring

No output schema declared.

No examples provided.

resume_agent_run ~25

Resume a paused Algenta agent run.

NameTypeReqDescription
run_idstringyes

No output schema declared.

No examples provided.

retrain_dataset ~48

Re-trigger semantic training for a dataset. Use after schema changes, alias updates, or to force a fresh model build.

NameTypeReqDescription
dataset_idstringyes
epochsinteger

No output schema declared.

No examples provided.

revoke_api_key ~25

Revoke one API key by id.

NameTypeReqDescription
key_idstringyes

No output schema declared.

No examples provided.

revoke_device ~29

Revoke one registered device by registration id for the current organization.

NameTypeReqDescription
registration_idstringyes

No output schema declared.

No examples provided.

route_capabilities ~92

Route an objective to the best unified capability with fallbacks and an authoritative execution_owner.

NameTypeReqDescription
artifact_affinitiesarray
binding_idsarray
execution_ownersarray
kindsarray
max_fallbacksinteger
objectivestringyes
provider_idsarray
tagsarray

No output schema declared.

No examples provided.

run_repository_fix ~45

Run repository pipeline then apply the result, returning the canonical repository envelope.

NameTypeReqDescription
applyobject
pipelineobject
repository_idstringyes

No output schema declared.

No examples provided.

run_repository_pipeline ~115

Run the repository snapshot->triage->plan->simulate chain and return the canonical repository envelope.

NameTypeReqDescription
max_evidence_itemsinteger
max_snippet_linesinteger
modelstring
repository_idstringyes
runsinteger
seedinteger
signalsobject
snapshotobject
snapshot_idstring
stop_afterstring
token_budgetinteger

No output schema declared.

No examples provided.

score ~57

Score a single simulation request with explicit weights and return the decision envelope plus score breakdown.

NameTypeReqDescription
requestobjectyesSimulation request forwarded to POST /v1/score.
scoring_weightsobjectOptional expected_value/downside_risk weights.

No output schema declared.

No examples provided.

simulate ~155

Run a Monte Carlo simulation and get a structured decision recommendation. Use for: quantifying risk in a decision, comparing expected outcomes, getting probability-weighted recommendations.

NameTypeReqDescription
modestringauto = minimal setup; expert = full distribution control
n_simulationsintegerMonte Carlo iteration count. Auto mode accepts 100–100,000; expert mode accepts 100–1,000,000.
objectivestringAuto-mode objective. For expert mode, use objective_function.
objective_functionstringExpert-mode expression, for example 'revenue - cost'. Required when mode='expert'.
variablesarrayyesInput variables as triangular distributions (low, most-likely, high)

No output schema declared.

No examples provided.

simulate_repository ~69

Simulate repository patch risk and return the gated DecisionEnvelope, resolving snapshot_id from the decision plan when omitted.

NameTypeReqDescription
decision_plan_idstringyes
repository_idstringyes
runsinteger
seedinteger
snapshot_idstring

No output schema declared.

No examples provided.

simulate_repository_patch ~54

Simulate an in-flight repository patch and return the canonical repository envelope.

NameTypeReqDescription
confidencenumber
patch_diffstringyes
repository_idstringyes
snapshot_idstringyes

No output schema declared.

No examples provided.

submit_job ~81

Submit a long-running async simulation job. Use for n_simulations > 500,000 or when you need a callback. Returns a job_id — poll with get_job_status.

NameTypeReqDescription
callback_urlstringWebhook URL for completion notification
n_simulationsinteger
objectivestring
variablesarrayyes

No output schema declared.

No examples provided.

test_capability_binding ~85

Test a saved capability binding or preview-test an unsaved one.

NameTypeReqDescription
binding_idstring
configobject
customer_metadataobject
execution_ownerstring
profile_idstring
provider_idstring
scopestring
scope_refstring

No output schema declared.

No examples provided.

test_connector ~32

Run a real connectivity test for one saved connector and persist its live/error status.

NameTypeReqDescription
connector_idstringyes

No output schema declared.

No examples provided.

test_webhook_delivery ~41

Send a test webhook payload to a callback URL and return the delivery result.

NameTypeReqDescription
callback_urlstringyesURL that should receive the test webhook payload.

No output schema declared.

No examples provided.

tokenize ~36

Tokenize UTF-8 text with a supported deterministic Algenta tokenizer model.

NameTypeReqDescription
inputstringyes
modelstring

No output schema declared.

No examples provided.

triage_repository ~77

Triage a repository snapshot into a bounded workspace evidence bundle with suspect files and symbols.

NameTypeReqDescription
max_evidence_itemsinteger
max_snippet_linesinteger
repository_idstringyes
signalsobjectyes
snapshot_idstringyes
token_budgetinteger

No output schema declared.

No examples provided.

update_connector ~57

Update one saved connector name, description, visibility, or config.

NameTypeReqDescription
configobject
connector_idstringyes
descriptionstring
namestring
visibilitystring

No output schema declared.

No examples provided.

update_execution_policy ~56

Update one or more execution-policy thresholds for the active organization.

NameTypeReqDescription
allow_reexecutionboolean
min_confidencenumber
require_calibrationboolean
risk_floornumber

No output schema declared.

No examples provided.

update_me ~38

Update the current user name and or organization name for the active API key.

NameTypeReqDescription
namestring
org_namestring

No output schema declared.

No examples provided.

update_team_member_role ~36

Update one current organization team member role by user id.

NameTypeReqDescription
rolestringyes
user_idstringyes

No output schema declared.

No examples provided.

Common questions

What is the Algenta MCP Server server?

Algenta MCP Server is listed in the public MCP registry as io.github.thyn-ai/algenta. Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP. This page covers its PyPI package (algenta-mcp).

Is the Algenta MCP Server server safe to use?

Algenta MCP Server scores 63 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Algenta MCP Server server expose?

Algenta MCP Server exposes 140 tools: onboard_dataset, list_datasets, get_dataset_status, retrain_dataset, connect_data, and 135 more. Their descriptions and schemas cost roughly 8,616 tokens of context every time the server is loaded.

Is the Algenta MCP Server server still maintained?

Algenta MCP Server is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.