// SCAN REPORT

Tuning Engines - LLM Fine-Tuning

73 tools. 26 can modify or destroy data without limits.

7 destructive tools with no built-in limits. Policy required.

Last updated:

26 can modify or destroy data
47 read-only
73 tools total

Community server · catalogue entry verified 29/06/2026

How to control Tuning Engines - LLM Fine-Tuning ↓

TOOL MAP

What Tuning Engines - LLM Fine-Tuning exposes to your agents

Read (47) Write / Execute (19) Destructive / Financial (7)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS
Critical Risk

The most dangerous Tuning Engines - LLM Fine-Tuning tools

Destructive · High tenant_invitation_cancel Cancel a pending tenant invitation. Requires tenant owner/admin API token. Destructive · High tenant_resource_delete Delete or revoke an allowlisted tenant resource. Requires tenant owner/admin API token. Destructive · High tenant_team_remove Remove a tenant member. Requires tenant owner/admin API token. Destructive · High cancel_evaluation Cancel a running or queued evaluation.

26 of Tuning Engines - LLM Fine-Tuning's 73 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Tuning Engines - LLM Fine-Tuning

PolicyLayer is an MCP gateway — it sits between your AI agents and Tuning Engines - LLM Fine-Tuning, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "cancel_evaluation": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "apply_insight": {
    "limits": [
      {
        "counter": "apply_insight_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "accept_insight": {
    "limits": [
      {
        "counter": "accept_insight_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Tuning Engines - LLM Fine-Tuning — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON TUNING ENGINES - LLM FINE-TUNING →

Instant setup, no code required.

FULL CATALOGUE

All 73 Tuning Engines - LLM Fine-Tuning tools

DESTRUCTIVE 7 tools
Destructive cancel_evaluation Cancel a running or queued evaluation. Destructive cancel_job Cancel a running or queued fine-tuning job. The job will be charged for any GPU time already used. Destructive delete_dataset Delete a dataset from the platform. Destructive delete_model Delete a trained model from cloud storage. Destructive tenant_invitation_cancel Cancel a pending tenant invitation. Requires tenant owner/admin API token. Destructive tenant_resource_delete Delete or revoke an allowlisted tenant resource. Requires tenant owner/admin API token. Destructive tenant_team_remove Remove a tenant member. Requires tenant owner/admin API token.
EXECUTE 2 tools
Execute doctor_simulate Run an Inference Doctor simulation for access, role, endpoint, policy, and resource debugging. Execute record_outcome Record an outcome or goal success signal for a run. Requires --enable-registry-writes because it writes teleme
WRITE 17 tools
Write apply_insight Apply or queue the approved action for an accepted Insight Loop recommendation. Requires --enable-registry-wri Write approve_approval Approve a pending policy approval request. Requires tenant owner/admin API token. Write catalog_export_status Check the status of a Marketplace export operation. Returns status, charge info, and any error messages. Write create_dataset Create dataset metadata for fine-tuning or evaluation. Write create_evaluation Create a new model evaluation. Run your trained model or a base model against a dataset using selected evaluat Write create_job Fine-tune an LLM on a GitHub repository using Tuning Engines. Write create_trace Ingest or update a runtime trace. Include run_id/request_id and normalized event types when possible. metadata Write generate_policy_draft Generate an AI-assisted AGT YAML draft. Drafts are disabled/shadow and must be reviewed/tested/saved explicitl Write inference_capture_update Update request-capture settings. Use credential_source_id references; raw cloud secrets are refused by MCP. Write map_outcome Create an outcome mapping rule for events that omitted outcome_key/goal_key. Requires --enable-registry-writes Write tenant_domains_update Replace the tenant Write tenant_resource_create Create an allowlisted tenant resource using non-secret JSON. MCP refuses raw secret fields and inference-key c Write tenant_resource_update Update an allowlisted tenant resource using non-secret JSON. MCP refuses raw secret fields; use CLI/web UI for Write tenant_team_disable Disable a tenant member and block API access. Requires tenant owner/admin API token. Write tenant_team_enable Re-enable a disabled tenant member. Requires tenant owner/admin API token. Write tenant_team_invite Invite a tenant member by email. Invitation token is emailed by the app and is never returned. Write tenant_team_set_inference_role Assign or clear an inference role for a tenant member. Requires tenant owner/admin API token.
READ 47 tools
Read accept_insight Accept an Insight Loop recommendation as valid for review. Requires --enable-registry-writes. Does not change Read dataset_status Check the status of a dataset import or processing operation. Read deny_approval Deny a pending policy approval request. Requires tenant owner/admin API token. Read estimate_evaluation Get a cost estimate for an evaluation before running it. Read estimate_job Get a cost estimate for a fine-tuning job before submitting it. Returns estimated cost, cost range, current ba Read evaluation_status Get live status of an evaluation including progress and current metrics. Read get_account Get your Tuning Engines account details and settings. Read get_balance Check your Tuning Engines account balance and recent transactions. Read get_catalog_model Get detailed information about a specific pre-built model or dataset from the Marketplace including descriptio Read get_inference_jwt Get a JWT token for authenticating with the Tuning Engines inference API. Read get_inference_token Exchange an inference key (sk-te-...) for a short-lived inference JWT. Read inference_capture_show Show request-capture settings for fine-tuning data capture. Secret values are not returned. Read inference_usage Get inference API usage statistics including request counts, token usage, and costs. Read job_status Get live status of a fine-tuning job including current status, GPU minutes used, estimated charges, remaining Read list_agents List available agents configured for your organization. Agents are AI assistants with specific capabilities an Read list_approvals List policy approval requests for the current tenant. Requires tenant owner/admin API token. Read list_catalog_models List available pre-built models and datasets from the Tuning Engines Marketplace. Read list_datasets List datasets available for training and evaluation. Datasets can be uploaded from S3 and used for fine-tuning Read list_evaluations List model evaluations. Evaluations run your trained models against benchmark datasets using various evaluator Read list_evaluators List available evaluators for model evaluation. Evaluators measure different aspects of model quality like cod Read list_inference_models List models available for inference through the Tuning Engines inference API. Read list_insights List Insight Loop recommendations. Read list_jobs List fine-tuning training jobs on Tuning Engines. Returns recent jobs with status, base model, agent type, GPU Read list_models List your trained and imported models on Tuning Engines. Read list_outcomes List observed outcomes, goals, workflow statuses, evals, and feedback normalized into success signals. Read list_policy_decisions List AGT YAML policy decisions for the current tenant. Requires tenant owner/admin API token. Read list_policy_templates List curated AGT YAML policy templates. Requires tenant owner/admin API token. Read list_supported_models List the supported base HuggingFace models available for fine-tuning on Tuning Engines. Optionally filter by a Read list_tenant_resources List tenant-admin resource names available through the public API. Internal proxy routes are intentionally not Read list_traces List runtime traces emitted by LangGraph, Temporal, MCP, skills, agents, or custom runtimes. Requires a tenant Read model_status Check the status of a model import or export operation. Read render_policy_template Render a curated AGT YAML policy template into disabled/shadow YAML. Template params must not include secrets. Read retry_job Retry a failed fine-tuning job from its last checkpoint. Creates a new job that resumes training where the fai Read show_agent Get details of a specific agent including capabilities, tools, and configuration. Read show_approval Show one policy approval request with redacted context. Requires tenant owner/admin API token. Read show_dataset Get details of a specific dataset including status, source, and metadata. Read show_evaluation Get full details of a specific evaluation including status, scores, metrics, and comparison data. Read show_insight Show one Insight Loop recommendation. Read show_job Get full details of a specific fine-tuning job including status, base model, agent type, GPU minutes, cost, er Read show_model Get details of a specific trained model. Read show_policy_decision Show one policy decision with redacted context and metadata. Requires tenant owner/admin API token. Read show_trace Show one runtime trace by run_id, including events, policy decisions, and approvals when linked. Read tenant_resource_list List an allowlisted tenant resource. Requires tenant owner/admin API token. Read tenant_resource_show Show one allowlisted tenant resource. Secret values are not returned by the API. Read tenant_resource_validate Validate an unsaved guardrail or AGT governance policy without creating records. Requires tenant owner/admin A Read tenant_team_list List tenant members, pending invitations, and allowed email domains. Requires tenant owner/admin API token. Read test_governance_policy Dry-run an AGT YAML governance policy against a JSON context. Requires tenant owner/admin API token.
EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Yaver 1060 tools
adminautomation
Nodebench 824 tools
adminautomation
Binance MCP Server 734 tools
adminautomation
Fortimanager 584 tools
adminautomation
Crow 573 tools
adminautomation
GoHighLevel MCP Server 566 tools
adminautomation
Huly 470 tools
adminautomation
Livepilot 467 tools
adminautomation
FAQ

Questions about Tuning Engines - LLM Fine-Tuning

Can an AI agent delete data through the Tuning Engines - LLM Fine-Tuning MCP server? +

Yes. The Tuning Engines - LLM Fine-Tuning server exposes 7 destructive tools including cancel_evaluation, cancel_job, delete_dataset. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Tuning Engines - LLM Fine-Tuning? +

The Tuning Engines - LLM Fine-Tuning server has 17 write tools including apply_insight, approve_approval, catalog_export_status. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Tuning Engines - LLM Fine-Tuning.

How many tools does the Tuning Engines - LLM Fine-Tuning MCP server expose? +

73 tools across 4 categories: Destructive, Execute, Read, Write. 47 are read-only. 26 can modify, create, or delete data.

How do I enforce a policy on Tuning Engines - LLM Fine-Tuning? +

Register the Tuning Engines - LLM Fine-Tuning MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Tuning Engines - LLM Fine-Tuning tool call.

Deterministic rules across all 73 Tuning Engines - LLM Fine-Tuning tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON TUNING ENGINES - LLM FINE-TUNING →

Instant setup, no code required.

73 Tuning Engines - LLM Fine-Tuning tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.