Apiosk

160 tools. 112 can modify or destroy data without limits.

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

Last updated:

112 can modify or destroy data
48 read-only
160 tools total
Read (48) Write / Execute (108) Destructive / Financial (4)

Destructive tools (apiosk_delete_api, apiosk_delete_wallet, apiosk_delete_wallet_api_key) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (agent-mollie-hosted-checkout, apiosk_buy_credits, apiosk_configure) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

Execute tools (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa, agent-account-intel-pack, agent-competitor-grid) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

One command. Full control.

Intercept sits between your agent and Apiosk. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @apiosk-mcp-server
Scans every tool. Generates a policy. Starts enforcing.
Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client
Deny destructive operations
apiosk_delete_api:
  rules:
    - action: deny

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

Rate limit write operations
agent-mollie-hosted-checkout:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
agent-case-study-extract:
  rules:
    - rate_limit: 60/minute

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

EXECUTE 91 tools
Execute aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa Execute agent-account-intel-pack Execute agent-competitor-grid Execute agent-email-verifier Execute agent-file-converter Execute agent-html-metadata Execute agent-integration-discovery-pack Execute agent-integration-fit Execute agent-invoice-parser Execute agent-json-diff Execute agent-lead-enricher Execute agent-market-map Execute agent-mollie-methods Execute agent-mollie-payment-link Execute agent-openapi-diff Execute agent-page-to-json Execute agent-policy-diff Execute agent-pricing-intelligence-pack Execute agent-procurement-pack Execute agent-prospect-research Execute agent-release-notes-to-tasks Execute agent-robots-sitemap Execute agent-scout Execute agent-sdk-surface-map Execute agent-signup-flow-mapper Execute agent-url-unshorten Execute agent-vendor-due-diligence-pack Execute agent-website-change-intel-pack Execute agent-website-diff Execute analytics-api Execute apiosk_execute Execute apiosk_help Execute apiosk_wallet_reveal_secret Execute apiosk-company-demo-agent-bundle Execute apiosk-company-demo-api Execute apiosk-company-demo-domain-intel Execute apiosk-company-demo-website-intel Execute auth-api Execute bella-pizza Execute code-review-skill Execute code-runner Execute codex-fresh-payout-1773067393 Execute codex-jsonplaceholder-10c-20260408 Execute codex-live-payout-1773067114824 Execute company Execute converter Execute crypto Execute crypto-metrics-dataset Execute email-verifier Execute gotobi Execute graph-nexus-api Execute html-metadata Execute hugen-scout Execute hugen-weather Execute invoice Execute invoice-parser Execute json Execute json-diff Execute maps-api Execute neural-sync-01 Execute news Execute notifications-api Execute notion-connector Execute ocr Execute payments-api Execute pdf Execute pet-store-api Execute prices Execute prompt-optimizer-skill Execute research-brief-skill Execute robots Execute robots-sitemap Execute scout Execute shopflow-api Execute shopflow-api-mlcfj3jv Execute shopflow-api-mlipyc8c Execute slack-connector Execute startup-funding-dataset Execute template-pack-product Execute tiamat-privacy-proxy Execute url-unshorten Execute users Execute video-transcription Execute vision-flux-v4 Execute vox-transcribe-pro Execute weather Execute web-diff Execute webhook-service Execute website-diff Execute workflow-service Execute zeppay
Can an AI agent delete data through the Apiosk MCP server? +

Yes. The Apiosk server exposes 4 destructive tools including apiosk_delete_api, apiosk_delete_wallet, apiosk_delete_wallet_api_key. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Apiosk? +

The Apiosk server has 17 write tools including agent-mollie-hosted-checkout, apiosk_buy_credits, apiosk_configure. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

How many tools does the Apiosk MCP server expose? +

160 tools across 4 categories: Destructive, Execute, Read, Write. 48 are read-only. 112 can modify, create, or delete data.

How do I add Intercept to my Apiosk setup? +

One line change. Instead of running the Apiosk server directly, prefix it with Intercept: intercept -c apiosk.yaml -- npx -y @apiosk-mcp-server. Download a pre-built policy from policylayer.com/policies/apiosk and adjust the limits to match your use case.

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init
Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.
// GET IN TOUCH

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

Message sent.

We'll get back to you soon.