SystemPrompt Reports MCP

An official MCP server provided by systemprompt.io that generates paid EU AI Act compliance reports. It performs deterministic Annex III classification, obligation gap analysis, Annex IV checklist generation, and provides remediation plans for AI systems. The service is integrated into the systemprompt.io governance infrastructure and charges $1.50 per call via Stripe or x402.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by systemprompt.io

You need:Paid structured report ($1.50 per call)

MCP endpoint (Streamable HTTP)

https://systemprompt.io/api/v1/mcp/systemprompt-reports/mcp

Vendor documentation

What its tools do

2 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

2 of 2 have a description · 2 of 2 declare behavior hints · 1 of 1 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 7, 2026, 3:54 AM UTC
Passed Official MCP Registry namespace is tied to systemprompt.io · Nov 7, 2026, 12:20 AM UTC
Passed Endpoint is on the registry namespace domain · Nov 7, 2026, 12:20 AM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Generate EU AI Act compliance reports for AI agents
Perform Annex III risk classification
Analyze obligation gaps in AI systems
Create remediation plans for compliance

Source and maintenance

Vendor evidenceRegistry 1.0.0

mcp-registry: io.systemprompt/reports@1.0.0 Project website

Protocol and capabilities

Server: systemprompt-reports 1.0.0
MCP protocol negotiated in check: 2025-11-25
Tools: 2 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {},
  "experimental": {
    "io.modelcontextprotocol/ui": {
      "mimeTypes": [
        "text/html;profile=mcp-app"
      ]
    },
    "io.modelcontextprotocol/tasks": {}
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Paid, decision-ready AI reports from systemprompt.io, priced per call with no account, no API key, and no subscription. Discovery (initialize, tools/list) is always free and every tool description states its exact price. The tool list returned by tools/list is authoritative; new report tools appear there as they launch. The free info tool returns a full usage guide for every tool on this server, including exact input requirements and payment steps, and never returns a 402; call it first. Current catalog: info (free) returns the usage guide. eu_ai_act_compliance ($1.50) generates an EU AI Act compliance report from a system description, model card, and data-flow document: a deterministic Annex III decision-tree classification, an article-by-article obligation gap analysis with quoted evidence, an Annex IV documentation checklist, and a remediation plan sequenced against the 2 August 2026 enforcement deadline. The response contains the report as markdown plus structured JSON and a branded PDF download link (valid 72 hours). Payment (two rails, same price): call a tool unpaid to receive HTTP 402 with exact PaymentRequirements. Crypto: sign an EIP-3009 USDC authorization on Base for the stated amount and retry with the X-PAYMENT header (x402 protocol). Card: open the Stripe checkout link in the 402 response, pay, then retry the same call with the checkout session id in an X-REDEMPTION-TOKEN header. Inputs are validated before payment, so an invalid call is never charged, and retrying the same paid request within ten minutes returns the cached report without a second charge. Catalog and docs: https://systemprompt.io/mcp • https://systemprompt.io/tools/eu-ai-act-compliance-report/

Tools

2 advertised

info — Usage guide

Advertised by the server during the last successful anonymous check.

Advertised read-only

Free usage guide for this server. Explains how the paid report tools work: exact input requirements, per-call pricing, and how to complete payment via x402 (USDC on Base) or Stripe checkout. Costs nothing and never returns a 402. Call this first before any paid tool.

info input schema

{
  "type": "object",
  "title": "InfoInput",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": true
}

info output schema

{
  "type": "object",
  "title": "TextArtifact",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "content"
  ],
  "properties": {
    "title": {
      "type": [
        "string",
        "null"
      ]
    },
    "content": {
      "type": "string"
    },
    "x-artifact-type": {
      "type": "string",
      "default": "text"
    }
  },
  "x-artifact-type": "text"
}

info annotations

{
  "title": "Usage guide",
  "readOnlyHint": true,
  "openWorldHint": false
}

eu_ai_act_compliance — EU AI Act compliance report

Advertised by the server during the last successful anonymous check.

Advertised read-only

Generate a structured EU AI Act compliance report from a system description, model card, and data-flow document. Nothing is silently optional: system_description is always required (min 50 chars); model_card and data_flows each accept substantive content (min 50 chars) or the exact string 'declined' to explicitly opt out; and exactly one of decision_tree_answers (from the free risk classifier, becomes binding evidence) or skip_decision_tree: true must be sent. All of this is validated free of charge before payment. The deterministic Annex III decision tree runs on every call: user-supplied answers are binding, otherwise answers are AI-derived and recorded as such. The tree classification, article citations, obligations, and evidence checklist are returned verbatim in the report JSON, together with exact enforcement-timeline dates and the matched Annex III area from the curated dataset. A staged AI workflow then produces an article-by-article obligation gap analysis, a required-documentation checklist mapped to Annex IV, and a prioritised remediation plan. The report includes a deterministic input_coverage grade (full, partial, or description_only) computed from what was supplied versus declined, the full AI classification with rationale, a programmatic reconciliation check between the tree and the AI risk tier, and a citation audit that flags any implausible article references. Returns markdown plus structured JSON. Every paid call also generates a branded PDF report and returns its download link (valid 72 hours). Price: $1.50 per call, payable by card (Stripe checkout link in the 402 response) or USDC on Base (x402). Full documentation, inputs, and pricing: https://systemprompt.io/tools/eu-ai-act-compliance-report/ — more governance tools and reports at https://systemprompt.io/mcp

eu_ai_act_compliance input schema

{
  "type": "object",
  "title": "EuAiActComplianceInput",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "system_description",
    "model_card",
    "data_flows"
  ],
  "properties": {
    "data_flows": {
      "type": "string",
      "description": "Data-flow description: what data enters the system, where it comes from, where outputs go (minimum 50 characters), or the exact string 'declined' to explicitly decline. Declining lowers the report's input_coverage grade."
    },
    "model_card": {
      "type": "string",
      "description": "Model card or equivalent documentation (minimum 50 characters), or the exact string 'declined' to explicitly decline supplying one. Declining lowers the report's input_coverage grade."
    },
    "skip_decision_tree": {
      "type": [
        "boolean",
        "null"
      ],
      "description": "Set true to explicitly skip supplying decision-tree answers; the tree is then derived by AI and the skip is recorded in input_coverage. Exactly one of decision_tree_answers or skip_decision_tree: true must be sent."
    },
    "system_description": {
      "type": "string",
      "description": "Written description of the AI system: what it does, who uses it, what decisions it informs, and the context it operates in. Minimum 50 characters."
    },
    "decision_tree_answers": {
      "type": [
        "array",
        "null"
      ],
      "items": {
        "type": "integer",
        "format": "uint",
        "minimum": 0
      },
      "description": "Answer indices from the free EU AI Act risk classifier decision tree; the resulting classification becomes binding evidence. Required unless skip_decision_tree is true."
    }
  }
}

eu_ai_act_compliance output schema

{
  "type": "object",
  "title": "TextArtifact",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "content"
  ],
  "properties": {
    "title": {
      "type": [
        "string",
        "null"
      ]
    },
    "content": {
      "type": "string"
    },
    "x-artifact-type": {
      "type": "string",
      "default": "text"
    }
  },
  "x-artifact-type": "text"
}

eu_ai_act_compliance annotations

{
  "title": "EU AI Act compliance report",
  "readOnlyHint": true,
  "openWorldHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 718 ms
95th percentile latency: 718 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 7, 2026, 3:54 AM UTC · probe · passed · 718 ms · metadata changed · 2 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http systemprompt-reports-mcp https://systemprompt.io/api/v1/mcp/systemprompt-reports/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add systemprompt-reports-mcp --url https://systemprompt.io/api/v1/mcp/systemprompt-reports/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable systemprompt-reports-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "systemprompt-reports-mcp": {
      "url": "https://systemprompt.io/api/v1/mcp/systemprompt-reports/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "systemprompt-reports-mcp": {
      "type": "streamableHttp",
      "url": "https://systemprompt.io/api/v1/mcp/systemprompt-reports/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start systemprompt-reports-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "systemprompt-reports-mcp": {
      "type": "http",
      "url": "https://systemprompt.io/api/v1/mcp/systemprompt-reports/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http systemprompt-reports-mcp https://systemprompt.io/api/v1/mcp/systemprompt-reports/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://systemprompt.io/api/v1/mcp/systemprompt-reports/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "systemprompt-reports-mcp": {
      "serverUrl": "https://systemprompt.io/api/v1/mcp/systemprompt-reports/mcp"
    }
  }
}

Let your agent find its tools

Find servers like SystemPrompt Reports MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

See all 1,414

Do you run SystemPrompt Reports MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing