Support: support@tinplate.dev · Zero-Retention Edge Security Support Trust Center DPA GitHub Issues
MCP Manifest Security Linter & Tool Guard

Catch MCP Tool Poisoning, Rug Pulls & Over-Broad Permissions Before Agents Connect

Model Context Protocol (MCP) tool descriptions are injected directly into your LLM's system prompt. Tinplate gives you deterministic static linting for mcp.json manifests plus runtime argument, shell, SQL, and code guards.

Why Teams Use This Bundle

  • Detects hidden prompt-injection instructions inside MCP tool descriptions and parameter schemas
  • Flags over-broad filesystem roots (/), wildcard shell permissions, and untrusted remote SSE/HTTP servers
  • Zero payload logging — manifests and tool payloads stay in volatile V8 memory
Quickstart

Lint an MCP manifest & validate tool arguments in one call

curl -X POST "https://api.tinplate.dev/v1/mcp-manifest-linter" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_POLAR_API_KEY" \
  -d '{"manifest":{"mcpServers":{"filesystem":{"command":"npx","args":["-y","@modelcontextprotocol/server-filesystem","/"]}}},"strict_schemas":true}'

Included Edge Micro-APIs (5)

POST /v1/mcp-manifest-linter Tier 1

MCP Server Manifest & Tool Security Linter API

Audit MCP server manifests for hidden tool poisoning, shell risks, and excessive permissions.

POST /v1/tool-call-validator AI Safety & Agents

Agent Tool-Call Validator & Repairer API

Validate and auto-repair broken LLM tool-call arguments against your JSON Schema.

POST /v1/command-sql-guard Tier 1

Agent Shell Command & SQL Query Safety Firewall API

Audit agent shell commands and Text-to-SQL queries for RCE, reverse shells, and destructive SQL.

POST /v1/agent-code-guard Live

AI-Generated Code & CI Workflow Sandbox Auditor API

Audit LLM-generated Python, JS/TS, Shell, or GitHub Actions code for sandbox escapes before execution.

POST /v1/agent-action-receipts/issue AI Safety & Agents

Agent Action Receipts API

Issue and verify tamper-evident HMAC-signed receipts for autonomous AI agent actions.