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 20

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 20 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
apply_repository ~114

Apply a simulated repository decision as patch_only, local_branch, or remote_pr.

NameTypeReqDescription
base_branchstring
branch_namestring
commit_messagestring
decision_plan_idstringyes
modestringyes
pull_request_bodystring
pull_request_titlestring
repository_idstringyes
simulation_idstringyes
snapshot_idstring
write_permissionboolean

No output schema declared.

No examples provided.

approve_agent_run ~29

Approve an Algenta agent run waiting on manual approval.

NameTypeReqDescription
run_idstringyes

No output schema declared.

No examples provided.

batch ~40

Run multiple simulation requests in one call and return per-item success or failure details.

NameTypeReqDescription
itemsarrayyesSimulation requests forwarded to POST /v1/batch.

No output schema declared.

No examples provided.

browse_connector ~32

Browse one saved live connector to discover files, tables, endpoints, or items.

NameTypeReqDescription
connector_idstringyes

No output schema declared.

No examples provided.

cancel_agent_run ~24

Cancel an Algenta agent run.

NameTypeReqDescription
run_idstringyes

No output schema declared.

No examples provided.

cancel_job ~32

Cancel a queued or running async simulation job by id.

NameTypeReqDescription
job_idstringyesUUID of the async job

No output schema declared.

No examples provided.

chat_completions ~49

Run the deterministic Algenta utility chat surface. This is a tokenizer-backed utility route, not a provider-backed generative model.

NameTypeReqDescription
messagesarrayyes
modelstring

No output schema declared.

No examples provided.

compare ~56

Run named scenarios side by side and return the winner plus deltas versus the best scenario.

NameTypeReqDescription
runsinteger
scenariosarrayyesNamed scenarios forwarded to POST /v1/compare.
seedinteger

No output schema declared.

No examples provided.

connect_data ~351

High-level data onboarding flow. Use this instead of advanced connector/source tools for normal users. Connect data once, pick the table/file/endpoint, and get a reusable dataset_id. If the result status is needs_selection, call connect_data again with connection_id and the chosen selection.

NameTypeReqDescription
connection_configobjectLegacy compatibility field for connector credentials/config. Prefer connector.location and connector.auth.credentials.
connection_idstringExisting saved connection_id when resuming after selection.
connection_namestringOptional label for the saved connection.
connection_typestringLegacy compatibility field. Prefer connector.type with the canonical connector envelope.
connectorobjectCanonical connector envelope with type/location/auth/options. Preferred when the same request shape should work across Python Runtime, TypeScript Runtime, and MCP.
csvstringRaw CSV text for direct file_upload datasets.
dataset_namestringyesName to save and reuse later.
descriptionstring
excel_b64stringBase64-encoded Excel payload.
json_strstringRaw JSON text for direct file_upload datasets.
parquet_b64stringBase64-encoded Parquet payload.
providerstringLegacy compatibility field for provider selection. Prefer connector.type plus connector.location/auth/options.
recordsarrayInline JSON records for direct file_upload datasets.
selectionobjectLegacy compatibility field for chosen table/query/path. Use the selection object returned in choices when resuming a legacy connection flow.
urlstringURL for direct file_upload or API datasets.
visibilitystringShared requires admin/owner permissions.

No output schema declared.

No examples provided.

count_tokens ~33

Count tokens with a supported deterministic Algenta tokenizer model.

NameTypeReqDescription
inputstringyes
modelstring

No output schema declared.

No examples provided.

create_agent_run ~73

Create a persisted Algenta agent run lifecycle resource.

NameTypeReqDescription
approval_modestring
contextobject
max_stepsinteger
output_formatstring
start_pausedboolean
taskstringyes
toolsarray

No output schema declared.

No examples provided.

create_api_key ~46

Create a new API key and return its one-time raw_key value.

NameTypeReqDescription
device_limitinteger
expires_atstring
labelstringyes

No output schema declared.

No examples provided.

create_billing_checkout ~27

Create a Stripe Checkout session for the active organization.

NameTypeReqDescription
planstring

No output schema declared.

No examples provided.

create_billing_portal ~22

Create a Stripe Billing Portal session for the active organization.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

create_capability_binding ~82

Create one capability binding for a provider/profile pair.

NameTypeReqDescription
binding_namestringyes
configobject
customer_metadataobject
execution_ownerstring
profile_idstringyes
provider_idstringyes
scopestring
scope_refstring

No output schema declared.

No examples provided.

create_connector ~62

Create and save one connector configuration for later data onboarding, health checks, and schema browsing.

NameTypeReqDescription
configobject
connector_typestringyes
descriptionstring
namestringyes
visibilitystring

No output schema declared.

No examples provided.

create_deployment ~49

Request a new isolated deployment for the active organization.

NameTypeReqDescription
billing_markup_pctnumber
configobject
providerstring
regionstring

No output schema declared.

No examples provided.

create_repository_decision_plan ~67

Create one immutable repository DecisionPlan revision from a workspace evidence bundle, resolving snapshot_id from triage when omitted.

NameTypeReqDescription
modelstring
repository_idstringyes
snapshot_idstring
workspace_evidence_bundle_refstringyes

No output schema declared.

No examples provided.

create_repository_snapshot ~71

Create or reuse an immutable repository snapshot for a saved repository connector.

NameTypeReqDescription
exclude_patternsarray
include_patternsarray
max_file_size_bytesinteger
max_filesinteger
refstring
repository_idstringyes

No output schema declared.

No examples provided.

delete_connector ~23

Delete one saved connector by id.

NameTypeReqDescription
connector_idstringyes

No output schema declared.

No examples provided.

delete_decision ~29

Delete one decision-memory record by id.

NameTypeReqDescription
decision_idstringyesDecision ID to delete.

No output schema declared.

No examples provided.

delete_deployment ~28

Request deprovisioning for one deployment by id.

NameTypeReqDescription
deployment_idstringyes

No output schema declared.

No examples provided.

delete_trigger ~32

Remove a trigger. The trigger will no longer fire automatically.

NameTypeReqDescription
trigger_idstringyesTrigger ID to delete.

No output schema declared.

No examples provided.

disable_skill ~24

Disable one skill binding by binding id.

NameTypeReqDescription
binding_idstringyes

No output schema declared.

No examples provided.

disconnect_data ~35

Delete a saved dataset and disconnect it from future use.

NameTypeReqDescription
dataset_idstringyesDataset ID from connect_data or list_data.

No output schema declared.

No examples provided.

discover_capability_binding ~88

Discover capabilities for a saved capability binding or preview-discover 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.

embedding_similarity ~43

Score two caller-supplied embedding vectors with a supported similarity model.

NameTypeReqDescription
leftarrayyes
modelstring
rightarrayyes

No output schema declared.

No examples provided.

embeddings ~37

Generate deterministic lexical embeddings with the supported Algenta model.

NameTypeReqDescription
dimensionsinteger
inputyes
modelstring

No output schema declared.

No examples provided.

enable_skill ~67

Enable one prompt-skill as a first-class capability binding.

NameTypeReqDescription
artifact_affinitiesarray
descriptionstring
execution_ownerstring
instructionstringyes
skill_namestringyes
tagsarray

No output schema declared.

No examples provided.

execute_capability ~68

Execute one routed or known algenta_managed capability by capability id. client_managed routes must execute in the customer app or adapter path.

NameTypeReqDescription
binding_idstring
capability_idstringyes
inputobject
request_idstring

No output schema declared.

No examples provided.

execute_decision ~124

Dispatch a logged decision to an external webhook and persist the execution receipt.

NameTypeReqDescription
decision_idstringyesDecision ID from log_decision or list_decisions.
forcebooleanOverride the idempotency gate for one re-execution.
metadataobjectOptional key-value pairs merged into the webhook payload.
override_safetybooleanBypass confidence and risk-floor policy gates for this execution.
timeout_secondsnumberWebhook timeout in seconds.
webhook_urlstringyesHTTPS webhook that should receive the decision payload.

No output schema declared.

No examples provided.

execute_runtime_library ~61

Execute one public function from an Algenta runtime library. Call list_runtime_libraries first to discover exact module and function names.

NameTypeReqDescription
args
functionstringyes
modulestringyes
request_idstring

No output schema declared.

No examples provided.

fire_trigger ~82

Manually fire a trigger — evaluates its condition and runs the simulation template regardless of whether the threshold is currently met. Useful for testing triggers or forcing an immediate evaluation.

NameTypeReqDescription
forcebooleanWhen true, run simulation even if the condition is not currently met (default: false).
trigger_idstringyesTrigger ID from register_trigger or list_triggers.

No output schema declared.

No examples provided.

get_agent_run ~28

Fetch a persisted Algenta agent run by run_id.

NameTypeReqDescription
run_idstringyes

No output schema declared.

No examples provided.

get_agent_run_checkpoints ~29

Fetch persisted checkpoints for an Algenta agent run.

NameTypeReqDescription
run_idstringyes

No output schema declared.

No examples provided.

get_agent_run_events ~38

Fetch the append-only event stream for an Algenta agent run.

NameTypeReqDescription
limitinteger
run_idstringyes

No output schema declared.

No examples provided.

get_agent_run_mission_events ~39

Fetch canonical mission-event records for an Algenta agent run.

NameTypeReqDescription
limitinteger
run_idstringyes

No output schema declared.

No examples provided.

get_agent_run_telemetry ~38

Fetch runtime telemetry batches for an Algenta agent run.

NameTypeReqDescription
limitinteger
run_idstringyes

No output schema declared.

No examples provided.

get_analytics ~35

Get usage analytics: simulation volume, latency p95, outcome distributions.

NameTypeReqDescription
daysintegerLookback window in days

No output schema declared.

No examples provided.

get_audit_log_artifacts ~110

Get paginated immutable audit-log artifacts for the current organization.

NameTypeReqDescription
actionstring
actor_emailstring
content_hashstring
limitinteger
manifest_versionstring
pageinteger
policy_snapshot_idstring
request_hashstring
resource_typestring
resultstring
schema_snapshot_idstring

No output schema declared.

No examples provided.

get_audit_logs ~98

Get paginated audit logs for the current organization.

NameTypeReqDescription
actionstring
actor_emailstring
limitinteger
manifest_versionstring
pageinteger
policy_snapshot_idstring
request_hashstring
resource_typestring
resultstring
schema_snapshot_idstring

No output schema declared.

No examples provided.

get_billing_info ~22

Get current billing plan and subscription info for the active organization.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_capability ~33

Get one unified capability by capability id.

NameTypeReqDescription
capability_idstringyes
include_instructionboolean

No output schema declared.

No examples provided.

get_connector ~23

Fetch one saved connector by id.

NameTypeReqDescription
connector_idstringyes

No output schema declared.

No examples provided.

get_contract ~51

Get the machine-readable Algenta public contract. Use this when an agent needs the canonical discovery, summary, query, batch, SQL report, governed filter rules, CLI, or MCP entrypoints before planning tool use.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_data_schema ~39

Get a saved dataset plus its schema and relationship metadata by dataset_id.

NameTypeReqDescription
dataset_idstringyesDataset ID from connect_data or list_data.

No output schema declared.

No examples provided.

get_data_summary ~57

Get the low-token dataset selection summary for a saved dataset_id. Use this after list_data(search=..., compact=true) before paying for the full schema payload.

NameTypeReqDescription
dataset_idstringyesDataset ID from connect_data or list_data.

No output schema declared.

No examples provided.

get_dataset_status ~69

Get live training status and model tier for a specific dataset. model_tier: 'none' = deterministic only, 'base' = generic model, 'schema' = fully trained schema-specific model (best quality).

NameTypeReqDescription
dataset_idstringyesDataset ID from onboard_dataset or list_datasets.

No output schema declared.

No examples provided.

get_decision ~35

Fetch one decision-memory record by id.

NameTypeReqDescription
decision_idstringyesDecision ID from log_decision or list_decisions.

No output schema declared.

No examples provided.

get_deployment ~22

Fetch the current deployment for the active organization, if one exists.

Input schema present but exposes no named parameters.

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 20 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 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.