// SCAN REPORT

Cartesi Knowledge MCP Server

29 tools. 10 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

10 can modify or destroy data

19 read-only

29 tools total

Community server · catalogue entry verified 03/07/2026

How to control Cartesi Knowledge MCP Server ↓

TOOL MAP

What Cartesi Knowledge MCP Server exposes to your agents

Read (19) Write / Execute (6) Destructive / Financial (4)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Cartesi Knowledge MCP Server tools

Financial · Critical prepare_erc20_deposit_instructions This tool generates instructions for depositing ERC20 tokens (a financial operation involving crypto assets), including token approval and deposit transactions. Financial · Critical prepare_erc1155_batch_deposit_instructions prepare_erc1155_batch_deposit_instructions Financial · High prepare_erc1155_deposit_instructions Generate host-machine instructions for depositing a single ERC1155 id/amount via ERC1155SinglePortal: balance check, mint (first wallet only Financial · Critical prepare_eth_deposit_instructions prepare_eth_deposit_instructions

10 of Cartesi Knowledge MCP Server's 29 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Cartesi Knowledge MCP Server

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

Block financial tools by default

{
  "prepare_erc1155_batch_deposit_instructions": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

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

Rate limit write operations

{
  "prepare_cartesi_create_command": {
    "limits": [
      {
        "counter": "prepare_cartesi_create_command_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "build_debugging_context": {
    "limits": [
      {
        "counter": "build_debugging_context_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 Cartesi Knowledge 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 CARTESI KNOWLEDGE →

Instant setup, no code required.

FULL CATALOGUE

All 29 Cartesi Knowledge MCP Server tools

FINANCIAL 4 tools

Financial prepare_erc1155_batch_deposit_instructions prepare_erc1155_batch_deposit_instructions Financial prepare_erc1155_deposit_instructions Generate host-machine instructions for depositing a single ERC1155 id/amount via ERC1155SinglePortal: balance Financial prepare_erc20_deposit_instructions Generate host-machine instructions for depositing ERC20 tokens into a Cartesi application via ERC20Portal usin Financial prepare_eth_deposit_instructions prepare_eth_deposit_instructions

EXECUTE 4 tools

Execute prepare_cartesi_build_command prepare_cartesi_build_command Execute prepare_cartesi_run_command prepare_cartesi_run_command Execute prepare_erc721_deposit_instructions Generate host-machine instructions for depositing one ERC721 token into a Cartesi application via ERC721Portal Execute prepare_voucher_execution_instructions Generate cast commands for executing a Cartesi voucher.

WRITE 2 tools

Write prepare_cartesi_create_command prepare_cartesi_create_command Write send_input_to_application Generate host-machine instructions for sending an input to a running Cartesi application through the InputBox

READ 19 tools

Read build_debugging_context Build issue-focused context by combining relevant resources and documentation routes for a debugging query. Read fetch_resource_content Fetch external URL content — restricted to URLs from this server's own resources. Read get_article_content Returns the full inline body of an article resource. Read get_cartesi_app_logic_guidance get_cartesi_app_logic_guidance Read get_cartesi_jsonrpc_api_reference get_cartesi_jsonrpc_api_reference Read get_knowledge_taxonomy Return the canonical taxonomy of known tag titles and source titles in the knowledge base. Read get_repository_sync_status Get synchronization freshness and metadata for a repository-backed resource. Read get_resource_detail Get normalized metadata for a single resource by resource ID, with optional documentation routes. Read get_skill Returns the full inline body of a skill resource. Read identify_cartesi_project_version Returns complete v1.5 vs v2.0-alpha fingerprint table, CLI capability differences, and deployment flow referen Read list_articles list_articles Read list_doc_route_sections Returns distinct section names for a documentation resource so agents can filter routes precisely. Read list_resource_doc_routes List documentation routes for one documentation resource, optionally filtered by section. Read list_resources_for_source List resources associated with a specific source title. Read list_resources_for_tag List resources associated with a specific tag title. Read list_skills list_skills Read search_documentation_routes Search documentation routes across resources using query text with optional section, source, and tag filters. Read search_knowledge_resources Searches curated Cartesi resources and returns lightweight result cards with MCP URIs and external links, but Read summarize_knowledge_base summarize_knowledge_base

EXPLORE

Related servers

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

FAQ

Questions about Cartesi Knowledge MCP Server

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

Yes. The Cartesi Knowledge MCP Server server exposes 4 financial tools including prepare_erc1155_batch_deposit_instructions, prepare_erc1155_deposit_instructions, prepare_erc20_deposit_instructions. 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.

How do I prevent bulk modifications through Cartesi Knowledge MCP Server? +

The Cartesi Knowledge MCP Server server has 2 write tools including prepare_cartesi_create_command, send_input_to_application. 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 Cartesi Knowledge MCP Server.

How many tools does the Cartesi Knowledge MCP Server MCP server expose? +

29 tools across 4 categories: Execute, Financial, Read, Write. 19 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on Cartesi Knowledge MCP Server? +

Register the Cartesi Knowledge 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 Cartesi Knowledge MCP Server tool call.

Deterministic rules across all 29 Cartesi Knowledge MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CARTESI KNOWLEDGE →

Instant setup, no code required.

29 Cartesi Knowledge MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.