// SCAN REPORT

Qiskit Documentation MCP Server

71 tools. 28 can modify or destroy data without limits.

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

Last updated: 27 Jun 2026

28 can modify or destroy data

43 read-only

71 tools total

Community server · catalogue entry verified 27/06/2026

How to control Qiskit Documentation MCP Server ↓

TOOL MAP

What Qiskit Documentation MCP Server exposes to your agents

Read (43) Write / Execute (24) Destructive / Financial (4)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Qiskit Documentation MCP Server tools

Destructive · High cancel_job_tool Cancelling a job permanently stops its execution with no ability to undo the cancellation. Destructive · High delete_environment_tool The tool performs a delete operation, which is inherently irreversible and cannot be undone. Destructive · High delete_model_tool The tool performs a destructive operation that permanently removes a model without the ability to undo the action. Destructive · High delete_saved_account_tool The 'delete' operation is inherently destructive and cannot be undone.

28 of Qiskit Documentation MCP Server's 71 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Qiskit Documentation MCP Server

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

Deny destructive operations

{
  "cancel_job_tool": {
    "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

{
  "convert_qpy_to_qasm3_tool": {
    "limits": [
      {
        "counter": "convert_qpy_to_qasm3_tool_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "active_account_info_tool": {
    "limits": [
      {
        "counter": "active_account_info_tool_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

Create a free account and register Qiskit Documentation MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON QISKIT DOCUMENTATION →

Instant setup, no code required.

FULL CATALOGUE

All 71 Qiskit Documentation MCP Server tools

DESTRUCTIVE 4 tools

Destructive cancel_job_tool Cancel a specific job. Destructive delete_environment_tool Delete an environment. Destructive delete_model_tool Delete a model. Destructive delete_saved_account_tool delete_saved_account_tool

EXECUTE 16 tools

Execute ai_permutation_synthesis_tool ai_permutation_synthesis_tool Execute convert_qasm3_to_qpy_tool convert_qasm3_to_qpy_tool Execute generate_random_clifford_tool Generate a random Clifford element for testing. Execute generate_random_linear_function_tool Generate a random invertible linear function for testing. Execute generate_random_permutation_tool Generate a random permutation for testing synthesis. Execute hybrid_ai_transpile_tool hybrid_ai_transpile_tool Execute run_estimator_tool run_estimator_tool Execute run_sampler_tool run_sampler_tool Execute start_tensorboard_tool start_tensorboard_tool Execute start_training_tool start_training_tool Execute stop_tensorboard_tool Stop the running TensorBoard process. Execute stop_training_tool Stop a training session. Execute synthesize_clifford_tool synthesize_clifford_tool Execute synthesize_linear_function_tool synthesize_linear_function_tool Execute transpile_circuit_tool transpile_circuit_tool Execute wait_for_training_tool wait_for_training_tool

WRITE 8 tools

Write convert_qpy_to_qasm3_tool convert_qpy_to_qasm3_tool Write create_clifford_env_tool create_clifford_env_tool Write create_coupling_map_tool create_coupling_map_tool Write create_linear_function_env_tool create_linear_function_env_tool Write create_permutation_env_tool create_permutation_env_tool Write export_circuit_to_qasm_tool export_circuit_to_qasm_tool Write save_model_tool save_model_tool Write setup_ibm_quantum_account_tool Set up IBM Quantum account with credentials.

READ 43 tools

Read active_account_info_tool Get information about the currently active IBM Quantum account. Read active_instance_info_tool Get the Cloud Resource Name (CRN) of the currently active instance. Read ai_clifford_synthesis_tool ai_clifford_synthesis_tool Read ai_linear_function_synthesis_tool ai_linear_function_synthesis_tool Read ai_pauli_network_synthesis_tool ai_pauli_network_synthesis_tool Read ai_routing_tool ai_routing_tool Read analyze_circuit_tool analyze_circuit_tool Read available_instances_tool available_instances_tool Read batch_train_environments_tool batch_train_environments_tool Read compare_optimization_levels_tool compare_optimization_levels_tool Read extract_subtopologies_tool extract_subtopologies_tool Read find_optimal_qubit_chains_tool find_optimal_qubit_chains_tool Read find_optimal_qv_qubits_tool find_optimal_qv_qubits_tool Read get_backend_calibration_tool get_backend_calibration_tool Read get_backend_properties_tool get_backend_properties_tool Read get_coupling_map_tool get_coupling_map_tool Read get_environment_info_tool Get detailed information about a specific environment. Read get_fake_backend_coupling_map_tool get_fake_backend_coupling_map_tool Read get_job_results_tool get_job_results_tool Read get_job_status_tool Get status of a specific job. Read get_model_info_tool Get detailed information about a model. Read get_page_tool get_page_tool Read get_tensorboard_metrics_tool get_tensorboard_metrics_tool Read get_tensorboard_status_tool Check the status of the TensorBoard process. Read get_training_metrics_tool get_training_metrics_tool Read get_training_status_tool Get the status and metrics of a training session. Read least_busy_backend_tool Find the least busy operational backend. Read list_available_fake_backends_tool list_available_fake_backends_tool Read list_backends_tool List available IBM Quantum backends. Read list_environments_tool List all active RL environments. Read list_loaded_models_tool List all models currently loaded in memory. Read list_my_jobs_tool List user's recent jobs. Read list_saved_accounts_tool List all IBM Quantum accounts saved on disk. Read list_saved_models_tool List all models saved to disk. Read list_subtopology_shapes_tool list_subtopology_shapes_tool Read list_tensorboard_experiments_tool List available TensorBoard experiments from past training runs. Read list_training_sessions_tool List all training sessions. Read load_circuit_from_qasm_tool load_circuit_from_qasm_tool Read load_model_tool Load a saved model from disk. Read lookup_error_code_tool lookup_error_code_tool Read search_docs_tool search_docs_tool Read synthesize_permutation_tool synthesize_permutation_tool Read usage_info_tool Get usage statistics and quota information for the active instance.

EXPLORE

Related servers

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

FAQ

Questions about Qiskit Documentation MCP Server

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

Yes. The Qiskit Documentation MCP Server server exposes 4 destructive tools including cancel_job_tool, delete_environment_tool, delete_model_tool. 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 Qiskit Documentation MCP Server? +

The Qiskit Documentation MCP Server server has 8 write tools including convert_qpy_to_qasm3_tool, create_clifford_env_tool, create_coupling_map_tool. 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 Qiskit Documentation MCP Server.

How many tools does the Qiskit Documentation MCP Server MCP server expose? +

71 tools across 4 categories: Destructive, Execute, Read, Write. 43 are read-only. 28 can modify, create, or delete data.

How do I enforce a policy on Qiskit Documentation MCP Server? +

Register the Qiskit Documentation 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 Qiskit Documentation MCP Server tool call.

Deterministic rules across all 71 Qiskit Documentation MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON QISKIT DOCUMENTATION →

Instant setup, no code required.

71 Qiskit Documentation MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.