Loading…
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 7 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The algenta-mcp MCP server exposes 140 tools, focused primarily on developer, database, and AI capabilities. Its published description reads: "Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates algenta-mcp F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Cross-tool shadowing" and "Data-exfiltration parameters". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check algenta-mcp's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add algenta-mcp to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://api.algenta.ai/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Register a dataset for semantic querying. Pass column names, inline records, or raw CSV. The engine profiles roles automatically and starts background training. Queries work immediately via a fallback
List registered datasets and their current model tier. Use search plus compact mode for low-token discovery, then poll status or use the primary data tools once you choose a dataset.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: onboard_dataset
A tool description tries to alter the model’s use of another tool.
oll status with list_datasets).RecommendationDescriptions must describe only their own tool.
tool: connect_data
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: connect_data
A tool description tries to alter the model’s use of another tool.
is instead of advanced connector/source tools for normal users. Connect daRecommendationDescriptions must describe only their own tool.
tool: list_data
A tool description tries to alter the model’s use of another tool.
discovery, then get_data_schema on the chosen dataset_id.RecommendationDescriptions must describe only their own tool.
tool: get_data_summary
A tool description tries to alter the model’s use of another tool.
Use this after list_data(search=..., compact=true) before paying for theRecommendationDescriptions must describe only their own tool.
tool: register_source
A tool description tries to alter the model’s use of another tool.
ble by name via query_data. Safe to call multiple times — re-registrationRecommendationDescriptions must describe only their own tool.
tool: list_sources
A tool description tries to alter the model’s use of another tool.
g query_data or register_source.RecommendationDescriptions must describe only their own tool.
tool: list_connectors
A tool description tries to alter the model’s use of another tool.
Use this before get_connector, test_connector, or browse_connector.RecommendationDescriptions must describe only their own tool.
tool: simulate_repository
A tool description tries to alter the model’s use of another tool.
Simulate repository patch risk and return the gated DeciRecommendationDescriptions must describe only their own tool.
tool: run_repository_pipeline
A tool description tries to alter the model’s use of another tool.
->triage->plan->simulate chain and return the canonical repository envelRecommendationDescriptions must describe only their own tool.
tool: simulate_repository_patch
A tool description tries to alter the model’s use of another tool.
Simulate an in-flight repository patch and return the caRecommendationDescriptions must describe only their own tool.
tool: query_data
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
query_data Execute a structured query against connected data sources. Convert the useRecommendationAnnotate destructive tools and require human approval.
tool: query_batch
A tool description tries to alter the model’s use of another tool.
a dataset with list_data and get_data_summary. Each item reuses the sameRecommendationDescriptions must describe only their own tool.
tool: query_sql_report
A database tool exposes a query/sql parameter that is a free-form string with no allow-list or parameterisation constraint — a raw-string injection surface. A tool exposing structured filters or an `enum` of named queries does not fire.
unconstrained query parameter "sql"RecommendationExpose parameterised operations instead of a raw query string; never build queries from unvalidated model output.
tool: list_models
A tool description tries to alter the model’s use of another tool.
before calling tokenize, count_tokens, chat_completions, responses, embRecommendationDescriptions must describe only their own tool.
tool: responses
A tool description tries to alter the model’s use of another tool.
tion or lexical embeddings.RecommendationDescriptions must describe only their own tool.
tool: embedding_similarity
A tool description tries to alter the model’s use of another tool.
Score two caller-supplied embedding vectors with a suRecommendationDescriptions must describe only their own tool.
tool: rerank
A tool description tries to alter the model’s use of another tool.
pplied document embeddings deterministically.RecommendationDescriptions must describe only their own tool.
tool: product_agent_run
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "context"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: recommend
A tool description tries to alter the model’s use of another tool.
Compare multiple named actions/options and get a rankedRecommendationDescriptions must describe only their own tool.
tool: submit_job
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "callback_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: submit_job
A tool description tries to alter the model’s use of another tool.
_id — poll with get_job_status.RecommendationDescriptions must describe only their own tool.
tool: test_webhook_delivery
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "callback_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: create_agent_run
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "context"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: refresh_credits
A tool description tries to alter the model’s use of another tool.
tibility credit batch for a quota-governed managed runtime.RecommendationDescriptions must describe only their own tool.
tool: ingest_metering_events
A tool description tries to alter the model’s use of another tool.
ntime analytics batch.RecommendationDescriptions must describe only their own tool.
tool: get_contract
A tool description tries to alter the model’s use of another tool.
summary, query, batch, SQL report, governed filter rules, CLI, or MCPRecommendationDescriptions must describe only their own tool.
tool: log_decision
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "context"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: log_decision
A tool description tries to alter the model’s use of another tool.
n context. Call record_outcome later to close the feedback loop and measure prRecommendationDescriptions must describe only their own tool.
tool: record_outcome
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "outcome_notes"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: execute_decision
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "webhook_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: execute_decision
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: register_trigger
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
parameter "webhook_url"RecommendationRemove side-channel parameters; constrain tool inputs.
tool: register_trigger
A tool description tries to alter the model’s use of another tool.
s below $80k', 'simulate expansion if Downtown revenue exceeds $200k'.RecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: retrain_dataset
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "retrain_dataset"RecommendationScope tools to the minimum needed.
tool: disconnect_data
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "disconnect_data"RecommendationScope tools to the minimum needed.
tool: create_connector
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "create_connector"RecommendationScope tools to the minimum needed.
tool: update_connector
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "update_connector"RecommendationScope tools to the minimum needed.
tool: delete_connector
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "delete_connector"RecommendationScope tools to the minimum needed.
tool: create_repository_snapshot
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "create_repository_snapshot"RecommendationScope tools to the minimum needed.
tool: create_repository_decision_plan
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "create_repository_decision_plan"RecommendationScope tools to the minimum needed.
tool: simulate_repository
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "simulate_repository"RecommendationScope tools to the minimum needed.
tool: simulate_repository_patch
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "simulate_repository_patch"RecommendationScope tools to the minimum needed.
tool: query_data
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "query_data"RecommendationScope tools to the minimum needed.
tool: query_batch
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "query_batch"RecommendationScope tools to the minimum needed.
tool: query_sql_report
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "query_sql_report"RecommendationScope tools to the minimum needed.
tool: ingest_data
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ingest_data"RecommendationScope tools to the minimum needed.
tool: execute_runtime_library
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "execute_runtime_library"RecommendationScope tools to the minimum needed.
tool: create_capability_binding
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "create_capability_binding"RecommendationScope tools to the minimum needed.
tool: execute_capability
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "execute_capability"RecommendationScope tools to the minimum needed.
tool: test_webhook_delivery
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "test_webhook_delivery"RecommendationScope tools to the minimum needed.
tool: create_agent_run
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "create_agent_run"RecommendationScope tools to the minimum needed.
tool: update_team_member_role
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "update_team_member_role"RecommendationScope tools to the minimum needed.
tool: remove_team_member
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "remove_team_member"RecommendationScope tools to the minimum needed.
tool: create_billing_checkout
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "create_billing_checkout"RecommendationScope tools to the minimum needed.
tool: create_billing_portal
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "create_billing_portal"RecommendationScope tools to the minimum needed.
tool: update_execution_policy
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "update_execution_policy"RecommendationScope tools to the minimum needed.
tool: update_me
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "update_me"RecommendationScope tools to the minimum needed.
tool: create_api_key
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "create_api_key"RecommendationScope tools to the minimum needed.
tool: record_outcome
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "record_outcome"RecommendationScope tools to the minimum needed.
tool: delete_decision
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "delete_decision"RecommendationScope tools to the minimum needed.
tool: register_trigger
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "register_trigger"RecommendationScope tools to the minimum needed.
tool: delete_trigger
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "delete_trigger"RecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
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).
Re-trigger semantic training for a dataset. Use after schema changes, alias updates, or to force a fresh model build.
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 sta
List visible datasets for the current user. Use search plus compact mode first for low-token dataset discovery, then get_data_schema on the chosen dataset_id.
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.
Get a saved dataset plus its schema and relationship metadata by dataset_id.
Refresh a saved dataset from its original database/API/object-store origin.
Delete a saved dataset and disconnect it from future use.
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 t
Advanced tool. List all registered data sources for this org with their schema summaries. Use this to discover available tables before calling query_data or register_source.
Advanced tool. Get the full schema for a specific registered source: column types, cardinality, fill rates, formula relationships, and detected join keys to other sources.
List saved data connectors such as databases, APIs, and file-backed sources. Use this before get_connector, test_connector, or browse_connector.
Create and save one connector configuration for later data onboarding, health checks, and schema browsing.
Fetch one saved connector by id.
Update one saved connector name, description, visibility, or config.
Run a real connectivity test for one saved connector and persist its live/error status.
Browse one saved live connector to discover files, tables, endpoints, or items.
Run a real connectivity test for one inline connector definition without saving it.
Browse one inline connector definition without saving it to discover files, tables, endpoints, or items.
Delete one saved connector by id.
List globally supported Repository Intelligence languages and ranked support progress.
Create or reuse an immutable repository snapshot for a saved repository connector.
Fetch one immutable repository snapshot by repository_id and snapshot_id.
Triage a repository snapshot into a bounded workspace evidence bundle with suspect files and symbols.
Create one immutable repository DecisionPlan revision from a workspace evidence bundle, resolving snapshot_id from triage when omitted.
Query one persisted repository snapshot for dependency, dependent, and change-risk graph edges.
Simulate repository patch risk and return the gated DecisionEnvelope, resolving snapshot_id from the decision plan when omitted.
Run the repository snapshot->triage->plan->simulate chain and return the canonical repository envelope.
Simulate an in-flight repository patch and return the canonical repository envelope.
Run repository pipeline then apply the result, returning the canonical repository envelope.
Apply a simulated repository decision as patch_only, local_branch, or remote_pr.
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 re
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 contr
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 o
Auto-map tabular data to a simulation payload. Detects variable distributions, polarity (revenue=positive, cost=negative), units, and builds the objective function automatically. Set run_simulation=tr
List the current Algenta model catalog, including deterministic utility models and any provider-backed routed entries with their routing, failover, timeout, and auth metadata, including capability-spe
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.
Tokenize UTF-8 text with a supported deterministic Algenta tokenizer model.
Count tokens with a supported deterministic Algenta tokenizer model.
Run the deterministic Algenta utility chat surface. This is a tokenizer-backed utility route, not a provider-backed generative model.
Run the unified Algenta utility response surface over deterministic tokenization or lexical embeddings.
Generate deterministic lexical embeddings with the supported Algenta model.
Score two caller-supplied embedding vectors with a supported similarity model.
Rerank caller-supplied document embeddings deterministically.
List executable local-runtime Mojo libraries. Use this when you need the runtime-backed compute catalog rather than the governed data/query tools. This surface is local/runtime-backed only.
Execute one local-runtime Mojo library function by module and function name. Pass args as either a JSON object, array, scalar, or null. This surface is local/runtime-backed only and does not route thr
List unified capability providers across data, MCP, skills, native tools, and runtime libraries.
List capability bindings for the current organization.
Create one capability binding for a provider/profile pair.
Test a saved capability binding or preview-test an unsaved one.
Discover capabilities for a saved capability binding or preview-discover an unsaved one.
List unified capabilities filtered by kind, provider, or binding.
Get one unified capability by capability id.
Route an objective to the best unified capability with fallbacks and an authoritative execution_owner.
Execute one routed or known algenta_managed capability by capability id. client_managed routes must execute in the customer app or adapter path.
List skill capabilities from the unified capability plane.
Enable one prompt-skill as a first-class capability binding.
Disable one skill binding by binding id.
Build a structured Algenta DecisionPlan from a validated simulation-style request. Use this when the caller needs the plan summary without the full decision envelope.
Run the simple product decision helper and return the chosen action plus risk summary.
Run the simple product task-execution helper and return a compact task result.
Run the simple product optimization helper and return the best variable values.
Run the simple product retrieval helper over caller-supplied documents or a collection id.
Run the simple product forecast helper over a historical metric series.
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.
Compare multiple named actions/options and get a ranked recommendation. Use when you need to choose between two or more alternatives with uncertainty.
Score a single simulation request with explicit weights and return the decision envelope plus score breakdown.
Run multiple simulation requests in one call and return per-item success or failure details.
Run named scenarios side by side and return the winner plus deltas versus the best scenario.
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.
List async simulation jobs with pagination and optional status filtering.
Fetch the latest async simulation job status by id.
Wait for an async simulation job to reach a terminal state. Returns the final result when the job completes, or the terminal status when it fails, is cancelled, or times out.
Fetch the completed result payload for an async simulation job by id.
Cancel a queued or running async simulation job by id.
Send a test webhook payload to a callback URL and return the delivery result.
Create a persisted Algenta agent run lifecycle resource.
List persisted Algenta agent runs for the authenticated org.
Fetch a persisted Algenta agent run by run_id.
Fetch the append-only event stream for an Algenta agent run.
Fetch persisted checkpoints for an Algenta agent run.
Query persisted checkpoints across Algenta agent runs.
Fetch canonical mission-event records for an Algenta agent run.
Query canonical mission-event records across persisted Algenta agent runs.
Fetch runtime telemetry batches for an Algenta agent run.
Query runtime telemetry batches across persisted Algenta agent runs.
Resume a paused Algenta agent run.
Cancel an Algenta agent run.
Approve an Algenta agent run waiting on manual approval.
List available deployment providers and regions for the current organization.
Fetch the current deployment for the active organization, if one exists.
Request a new isolated deployment for the active organization.
Get current-month cost details for one deployment by id.
Request deprovisioning for one deployment by id.
List team members for the current organization.
Invite a team member to the current organization.
Update one current organization team member role by user id.
Remove one team member from the current organization by user id.
List registered devices for the current organization.
Revoke one registered device by registration id for the current organization.
Get paginated audit logs for the current organization.
Get paginated immutable audit-log artifacts for the current organization.
Get the current autonomous execution policy for the active organization.
List persisted execution-policy snapshots for the active organization.
Get current billing plan and subscription info for the active organization.
Create a Stripe Checkout session for the active organization.
Create a Stripe Billing Portal session for the active organization.
Issue a compatibility credit batch for a quota-governed managed runtime.
Ingest an explicitly enabled managed-runtime analytics batch.
Update one or more execution-policy thresholds for the active organization.
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 plannin
Get the signed Algenta runtime manifest. Use this when an agent needs the canonical runtime-core inventory, maturity states, proof matrix, typed failure contract, or release theorem before using runti
Get the authenticated Algenta runtime release validation result. Use this when an agent needs the current manifest-listed release verdict, formal theorem conditions, or fail-closed proof status before
Get the authenticated Algenta runtime module proof catalog. Use this when an agent needs the shipping module inventory, proof-matrix entries, maturity counts, or compiled module evidence before using
Get the authenticated Algenta runtime benchmark catalog. Use this when an agent needs benchmark classes, benchmark evidence paths, evaluation quality gates, SLO budgets, compiled artifacts, or module
Get current user and organization identity for the active API key.
Update the current user name and or organization name for the active API key.
Get current plan quotas and limits for the active API key.
List supported distribution types for the active API key.
List built-in simulation templates for the active API key.
List active API keys for the current organization. Never returns raw secret material.
Create a new API key and return its one-time raw_key value.
Revoke one API key by id.
List recent simulation runs with optional filters.
Fetch a single simulation run by ID.
Get usage analytics: simulation volume, latency p95, outcome distributions.
Get current billing period usage vs quota for this API key.
Persist a decision to the Decision Memory audit trail. Link to a simulation run_id to bind the full DecisionPlan context. Call record_outcome later to close the feedback loop and measure prediction ac
Retrieve the Decision Memory audit trail — all logged decisions, most recent first. Use with_outcome_only=true to see only decisions where actual results have been recorded. outcome_delta = actual_out
Fetch one decision-memory record by id.
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 a
Dispatch a logged decision to an external webhook and persist the execution receipt.
Delete one decision-memory record by id.
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: 'al
List all registered triggers with their current status, last-checked time, and last-fired simulation result summary.
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.
Pause or resume an existing trigger without deleting it.
Remove a trigger. The trigger will no longer fire automatically.