// SCAN REPORT

Respan MCP Server

60 tools. 27 can modify or destroy data without limits.

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

Last updated:

27 can modify or destroy data
33 read-only
60 tools total

Community server · catalogue entry verified 30/06/2026

How to control Respan MCP Server ↓

TOOL MAP

What Respan MCP Server exposes to your agents

Read (33) Write / Execute (23) Destructive / Financial (4)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS
Critical Risk

The most dangerous Respan MCP Server tools

Destructive · Critical delete_dataset This tool irreversibly deletes data at scale (an entire dataset plus associated logs), which cannot be recovered or reversed. Destructive · High delete_evaluator This tool irreversibly deletes data (an evaluator resource) with no recovery mechanism. Destructive · High delete_experiment This tool meets the Destructive category definition as it irreversibly deletes data (an experiment and its spans) and cannot be undone. Destructive · High remove_dataset_logs This tool deletes or removes log entries from a dataset, which cannot be undone.

27 of Respan MCP Server's 60 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Respan MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and Respan MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "delete_dataset": {
    "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
{
  "bulk_create_dataset_logs": {
    "limits": [
      {
        "counter": "bulk_create_dataset_logs_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "filter_workflows": {
    "limits": [
      {
        "counter": "filter_workflows_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 Respan MCP Server — 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 RESPAN →

Instant setup, no code required.

FULL CATALOGUE

All 60 Respan MCP Server tools

DESTRUCTIVE 4 tools
Destructive delete_dataset Permanently delete a dataset and all its logs. This action cannot be undone. Destructive delete_evaluator Permanently delete an evaluator. This action cannot be undone. Destructive delete_experiment Permanently delete an experiment and its spans. This action cannot be undone. Destructive remove_dataset_logs Remove one or more logs from a dataset by filter. To delete a single log, pass filter { unique_id: { operator:
EXECUTE 6 tools
Execute create_experiment Create and run an experiment. Processes a dataset Execute deploy_prompt_version Deploy a specific prompt version, making it the active version that experiments (and other workflows) will use Execute deploy_workflow Deploy a committed workflow/pipeline version as the active (live) version. Calls POST /api/workflows/{id}/dep Execute run_evaluator Run an evaluator on a single log/span to verify it works. This is for quick verification of one record (e.g. Execute test_evaluator Test-run a grader with sample inputs to verify it scores correctly BEFORE committing. Required keys in inputs Execute validate_workflow Validate a workflow by running it against a sample log. Returns validation results and any errors.
WRITE 17 tools
Write bulk_create_dataset_logs Create one or more logs in a dataset. Pass a single-item array to insert one log. Each log can include input, Write commit_evaluator Commit the current draft of a grader, creating a new read-only version. IMPORTANT: Only commit AFTER a succes Write commit_workflow Commit the current draft of a workflow/pipeline, locking it as a read-only version that can be deployed. REQU Write create_dataset Create a new dataset. MODES: - Empty dataset: pass is_empty=true. No time range needed. - Sampled from logs: Write create_evaluation_pipeline Create an evaluator pipeline (V2 — Blockly visual editor compatible) that renders in the Evaluators page UI. Write create_evaluator Create a new evaluator (grader). Evaluators score LLM outputs. REQUIRED: name, type, score_value_type. TYPES Write create_prompt Create a new prompt template. Only sets name and description. Use create_prompt_version to add content. Write create_prompt_version Create a new version of a prompt. The version is always created as NOT deployed. Write create_workflow Create a new workflow. Workflows are event-driven pipelines with chained tasks. TYPES: - Write import_dataset_logs Import existing logs into a dataset by time range and filters. Runs in the background. Write replace_dataset_log Replace (full overwrite) a log in a dataset. Updates input, output, expected_output, and/or metadata fields. Write update_dataset Update a dataset Write update_evaluation_pipeline Update an evaluator pipeline. Provide the FULL updated structure (steps, combine, weights). Existing graders a Write update_evaluator Update an existing evaluator Write update_prompt Update a prompt Write update_prompt_version Update an existing prompt version. Always keeps deploy: false. Write update_workflow Update a workflow
READ 33 tools
Read filter_workflows Filter workflows by type and other fields. Use the filters parameter to scope by type: - { Read get_customer_detail Retrieve detailed information about a specific customer including budget usage. Returns customer profile and Read get_dataset Retrieve detailed information about a specific dataset. Read get_evaluation_pipeline Get an evaluator pipeline by ID. Accepts both the family workflow_id and the version PK. Read get_evaluator Retrieve detailed information about a specific evaluator including its config. Read get_experiment Retrieve detailed information about a specific experiment by its ID. Read get_experiment_score_averages Compute average score per evaluator for an experiment by walking the spans client-side. Use this when the bac Read get_experiment_span Retrieve detailed information about a specific span within an experiment. Read get_log_detail Retrieve complete details of a single log via GET /api/request-logs/{id}/. Returns full information including Read get_prompt_detail Retrieve detailed information about a specific prompt. Returns complete prompt data including: - id: Unique p Read get_prompt_version_detail Retrieve detailed information about a specific version of a prompt. Returns complete version data including: Read get_spans_summary Retrieve aggregated summary statistics for log spans. Returns total_count, total_cost, total_tokens, avg_laten Read get_trace_tree Retrieve the complete hierarchical span tree of a single trace. Returns detailed trace information with the f Read get_workflow Retrieve detailed information about a workflow including its task definitions. Read get_workflow_version Retrieve a specific version of a workflow. Read list_customers List customers/users with pagination and sorting. Retrieves a paginated list of customers who have made API r Read list_dataset_eval_runs List evaluation run results for a dataset. Shows past eval runs with status and results. Read list_dataset_logs List all logs (data points) in a dataset with pagination and filtering. Read list_datasets List all datasets in your organization. Read list_evaluation_pipelines List evaluator pipelines (V2). These are the items shown on the Evaluation Pipelines page in the UI. Read list_evaluator_versions List all versions (commits) of an evaluator. Read list_evaluators List all evaluators in your organization with pagination. Read list_experiment_spans List all spans (execution traces) for a specific experiment. Read list_experiments List all experiments in your organization. Read list_logs List and filter LLM request logs. Supports pagination, sorting, time range, and server-side filtering. IMPORT Read list_prompt_versions List all versions of a specific prompt. Returns all versions of a prompt, allowing you to track changes over Read list_prompts List all prompts in your Respan organization. Returns a paginated list of all prompts you have created in Res Read list_traces List and filter traces with sorting, pagination, and server-side filtering. A trace represents a complete wor Read list_workflow_versions List all versions of a workflow. Read list_workflows List all workflows (automations, monitors, evaluator pipelines) in your organization. Read retrieve_dataset_log Retrieve a specific log from a dataset by its unique ID. Read summarize_dataset_logs Get aggregated summary statistics for logs in a dataset. Pass filters to scope the summary; omit filters to su Read undeploy_workflow Undeploy a workflow, stopping it from processing events.
EXPLORE

Related servers

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

Yaver 1060 tools
adminautomation
Nodebench 824 tools
adminautomation
UnClick 813 tools
adminautomation
Binance MCP Server 734 tools
adminautomation
Fortimanager 584 tools
adminautomation
Crow 573 tools
adminautomation
Mcp 571 tools
adminautomation
GoHighLevel MCP Server 566 tools
adminautomation
FAQ

Questions about Respan MCP Server

Can an AI agent delete data through the Respan MCP Server MCP server? +

Yes. The Respan MCP Server server exposes 4 destructive tools including delete_dataset, delete_evaluator, delete_experiment. 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 Respan MCP Server? +

The Respan MCP Server server has 17 write tools including bulk_create_dataset_logs, commit_evaluator, commit_workflow. 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 Respan MCP Server.

How many tools does the Respan MCP Server MCP server expose? +

60 tools across 4 categories: Destructive, Execute, Read, Write. 33 are read-only. 27 can modify, create, or delete data.

How do I enforce a policy on Respan MCP Server? +

Register the Respan MCP Server 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 Respan MCP Server tool call.

Deterministic rules across all 60 Respan MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON RESPAN →

Instant setup, no code required.

60 Respan MCP Server 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.