// SCAN REPORT

Sablier MCP Server

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

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

Last updated: 29 Jun 2026

28 can modify or destroy data

55 read-only

83 tools total

Community server · catalogue entry verified 29/06/2026

How to control Sablier MCP Server ↓

TOOL MAP

What Sablier MCP Server exposes to your agents

Read (55) Write / Execute (18) Destructive / Financial (10)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Sablier MCP Server tools

Financial · Critical manage_subscription The tool name 'manage_subscription' strongly implies management of financial subscriptions (creating, modifying, or cancelling paid plans). Financial · Critical buy_credit_pack The name 'buy_credit_pack' indicates a purchase action, which constitutes a financial transaction. Financial · Critical subscribe The tool name 'subscribe' strongly implies a financial subscription commitment. Destructive · High delete_feature_set This tool irreversibly deletes data (custom feature sets) and cannot be undone, matching the Destructive category definition.

28 of Sablier MCP Server's 83 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Sablier MCP Server

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

Block financial tools by default

{
  "buy_credit_pack": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Deny destructive operations

{
  "delete_feature_set": {
    "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

{
  "add_feature": {
    "limits": [
      {
        "counter": "add_feature_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_derivatives": {
    "limits": [
      {
        "counter": "analyze_derivatives_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 Sablier 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 SABLIER →

Instant setup, no code required.

FULL CATALOGUE

All 83 Sablier MCP Server tools

FINANCIAL 3 tools

Financial buy_credit_pack buy_credit_pack Financial manage_subscription manage_subscription

DESTRUCTIVE 7 tools

Destructive delete_feature_set Delete a custom feature set. Permanent, cannot be undone. Cannot delete shared templates. Destructive delete_flow_job Delete a flow simulation job (baseline or constrained scenario). Permanent, cannot be undone. Destructive delete_grain_analysis Delete a saved GRAIN qualitative analysis by ID. Permanent, cannot be undone. Destructive delete_model_group Delete a model group and all its models, simulations, and associated data. Permanent, cannot be undone. Destructive delete_portfolio Delete a portfolio by ID. Permanent, cannot be undone. Destructive delete_rule Permanently delete a systematic trading rule from a portfolio. Destructive delete_scenario Delete a saved scenario. Permanent, cannot be undone.

EXECUTE 7 tools

Execute backtest_rules backtest_rules Execute evaluate_rules evaluate_rules Execute forward_test_rules forward_test_rules Execute generate_flow_paths generate_flow_paths Execute simulate_flow_scenario simulate_flow_scenario Execute test_flow_risk test_flow_risk Execute train_flow_model train_flow_model

WRITE 11 tools

Write add_feature add_feature Write add_features_batch add_features_batch Write create_feature_set create_feature_set Write create_portfolio create_portfolio Write create_rule create_rule Write create_scenario create_scenario Write refresh_feature_data refresh_feature_data Write toggle_rule Activate or deactivate a systematic trading rule. Only active rules are included in forward_test_rules by defa Write update_portfolio update_portfolio Write update_rule update_rule Write update_scenario update_scenario

READ 55 tools

Read analyze_derivatives analyze_derivatives Read analyze_qualitative analyze_qualitative Read analyze_quantitative analyze_quantitative Read check_flow_job check_flow_job Read check_scenario_probability check_scenario_probability Read compute_betas compute_betas Read compute_correlations compute_correlations Read compute_returns compute_returns Read download_flow_paths download_flow_paths Read flow_validate flow_validate Read get_asset_profiles Get asset classification for a portfolio: sector, industry, country, exchange, and asset type per holding. Read get_billing_info get_billing_info Read get_billing_usage get_billing_usage Read get_credits get_credits Read get_earnings_calendar get_earnings_calendar Read get_efficient_frontier get_efficient_frontier Read get_feature_set Get detailed information about a specific feature set including all features and their configuration. Read get_flow_results get_flow_results Read get_fundamentals get_fundamentals Read get_grain_analysis Retrieve full results of a completed GRAIN analysis: theme scores, per-ticker breakdown, and evidence passages Read get_history get_history Read get_indices get_indices Read get_news get_news Read get_optimization_history get_optimization_history Read get_portfolio Get detailed information about a specific portfolio including assets, weights, and associated feature sets. Us Read get_portfolio_analytics get_portfolio_analytics Read get_portfolio_fact_sheet get_portfolio_fact_sheet Read get_portfolio_value Get the current live value of a portfolio: total value, P&L, and per-position breakdown. Read get_quotes get_quotes Read get_residual_correlation get_residual_correlation Read get_scenario Get detailed information about a saved scenario including its factor specs. Read get_sectors get_sectors Read get_top_movers get_top_movers Read get_vix_panel get_vix_panel Read get_yield_curve get_yield_curve Read list_credit_packs list_credit_packs Read list_feature_set_templates Browse pre-built sets of market drivers (e.g. interest rates, volatility, commodities). Returns template names Read list_feature_sets list_feature_sets Read list_flow_baselines list_flow_baselines Read list_flow_scenarios list_flow_scenarios Read list_grain_analyses List past qualitative (GRAIN) analyses. Optionally filter by portfolio_id. Read list_model_groups List all model groups (each created by analyze_quantitative). A model group ties a portfolio to a conditioning Read list_portfolios List the user Read list_rules List all systematic trading rules attached to a portfolio, including their trigger/action definitions, active Read list_scenarios list_scenarios Read list_simulations List past beta computation runs for a Moment model group. Each entry is a compute_betas invocation with its si Read list_themes Browse the GRAIN theme library. Returns predefined themes with names, descriptions, keywords, and categories. Read market_radar market_radar Read optimize_portfolio optimize_portfolio Read price_option price_option Read screen_universe screen_universe Read search_features search_features Read toggle_overage toggle_overage Read validate_rules validate_rules Read whoami whoami

EXPLORE

Related servers

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

FAQ

Questions about Sablier MCP Server

Can an AI agent move money through the Sablier MCP Server MCP server? +

Yes. The Sablier MCP Server server exposes 3 financial tools including buy_credit_pack, manage_subscription, subscribe. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

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

Yes. The Sablier MCP Server server exposes 7 destructive tools including delete_feature_set, delete_flow_job, delete_grain_analysis. 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 Sablier MCP Server? +

The Sablier MCP Server server has 11 write tools including add_feature, add_features_batch, create_feature_set. 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 Sablier MCP Server.

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

83 tools across 3 categories: Destructive, Read, Write. 55 are read-only. 28 can modify, create, or delete data.

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

Register the Sablier 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 Sablier MCP Server tool call.

Deterministic rules across all 83 Sablier MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SABLIER →

Instant setup, no code required.

83 Sablier MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.