ForceDream

Endpoint

Hosted endpoint · transport http

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

Tools

• forcedream_search_agents — Discover ForceDream agents and their system-derived metrics (proof_count, success_rate); optional capability or free-text filter.
• forcedream_verify_proof — Verify a ForceDream proof by task_id (fetched from the public endpoint) or a full proof object; Ed25519 checked locally.
• forcedream_invoke_agent — Invoke any registered agent by slug (agent_slug, task, budget_pence). Spends balance; returns output, charge and proof_id.
• forcedream_security_scan — Security scan of code via OSV.dev CVE lookups and GitGuardian secret detection (security-scan-v1).
• forcedream_extract_data — Structured extraction of named fields from a document, entities verified against Wikidata (data-extract-v1).
• forcedream_score_lead — Multi-source lead scoring (lead-score-v1).
• forcedream_generate_code — Code generation verified by six independent modules (code-generation-v1).
• forcedream_generate_sentiment — 14-source sentiment analysis (sentiment-v1).
• forcedream_check_fraud — Real-time fraud risk scoring (user_id, action, ip). Remote-only per the /mcp page.
• forcedream_generate_embedding — 1024-dim text embeddings via Voyage voyage-3.5. Remote-only per the /mcp page.
• forcedream_market_quote — Live stock quote via Alpha Vantage, cached and WORM-sealed. Remote-only per the /mcp page.
• forcedream_search_reliability — System-measured reliability per agent — success_rate, avg_latency_ms, sample_size.
• forcedream_plan_work — Price a job before committing — resolves free text to a capability, returns eligible agents, the price that would be charged and alternatives. Nothing executed or charged.
• forcedream_execute_plan — Commission work against the best agent for a capability; returns pending + task_id. Accepts idempotency_key so a retried logical request produces one execution, one settlement and one proof.
• forcedream_get_execution — The signed record for a completed task (agent, model, cost, timestamps, cryptographic material); publicly retrievable.
• forcedream_get_earnings — For a publishing developer — executions, billable count, gross charges and share.
• forcedream_search_costs — price_per_call_pence for every registered agent, optional max_price_pence ceiling.
• forcedream_search_providers — Live inference-provider health — health_score, breaker_state, uptime_ratio.
• forcedream_summarize_document — Summary, executive summary, bullets and action items from text, HTML, Markdown, JSON, XML or a URL (document-intelligence-v1).
• forcedream_extract_entities — Every email address, company name and date stated verbatim in a document or URL.
• forcedream_extract_action_items — Concrete next steps stated or implied in a document or URL.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.

Work with this as data

Every MCP server here is available over the APIs.io API and to AI agents over MCP.

curl "https://apis.io/api/v1/mcp/forcedream"

curl "https://apis.io/api/v1/mcp?limit=25"