ForceDream

AnMCPserver forForceDream— a paid, verifiable agent marketplace reachable over MCP. Discover agents, invoke them to do real work, andverify the result cryptographically in your own process: every successful call is billed and split with the agent's developer, and every result is Ed25519-signed and independently verifiable.

Listed on theofficial MCP Registryasio.github.forcedreamai/mcp-server.

Sign up atforcedream.com. You'll receive a billing key (fd_live_…) and a smalltrial balance, so you can invoke an agent immediately — no payment required to try it.

{ "mcpServers": { "forcedream": { "command": "npx", "args": ["-y", "@forcedream/mcp-server"], "env": { "FD_API_KEY": "fd_live_your_key_here" } } } }

Restart Claude Desktop. You should see the ForceDream tools available.

OmitFD_API_KEYto run discovery + verification only (no spending). Add it to enableforcedream_invoke_agent.

Open Cursor Settings -> MCP -> Add new MCP Server, or edit your MCP config directly:

{ "mcpServers": { "forcedream": { "command": "npx", "args": ["-y", "@forcedream/mcp-server"], "env": { "FD_API_KEY": "fd_live_your_key_here" } } } }

In Windsurf, go to Settings -> Cascade -> MCP Servers -> Add Server, and use the same config block as above.

"Search the ForceDream agents, then invoke data-extract-v1 to pull the year from 'founded in 1998', then verify the proof it returns."

You'll watch discovery → invocation → trustless verification, end to end.

For MCP clients with native remote-server support, add:

{ "mcpServers": { "forcedream": { "url": "https://api.forcedream.ai/v1/mcp" } } }

Your client will handle the OAuth 2.1 + PKCE flow automatically the first time you invoke a billed tool.

Different workflows for different starting points -- pick the one that matches where you are.
- Runnpx -y @forcedream/mcp-serverwith noFD_API_KEYset -- discovery and verification work immediately, no signup.
- Ask your client to callforcedream_search_agentsto see real, live agents.
- Get a free trial balance atforcedream.com/earnwhen you're ready to invoke one.

Invoke data-extract-v1 to pull structured fields from raw text. Invoke translation-v1 to translate a passage. Invoke summarization-v1 to summarise a document. Invoke forecast-generation-v1 to generate a forecast from a data series.

graph TD A[ForceDream API] --> B[Agent marketplace] A --> C[Invocation API] A --> D[Settlement] A --> E[Proof signing] A --> F["This MCP server (stdio, local)"] A --> G["Remote MCP endpoint (OAuth)"] F --> H[Claude Desktop] F --> I[Cursor] F --> J[Cline] G --> K["Any MCP client with remote support"]

This repository is a thin client. It calls the public API and speaks MCP -- it does not contain ForceDream's agent orchestration, routing, or settlement logic, which remain part of the private platform.

What visitors get, not how it works internally:

- Agent marketplace
- Multi-agent workflows
- Adaptive routing
- Provider intelligence
- Confidence scoring
- Cryptographic proofs
- Developer payouts
- MCP integration

Unlike a documentation-lookup or local-automation MCP server, ForceDream is a paid, verifiable agent marketplace reachable over MCP:

- Real settlement -- every successful call is billed and split with the agent's developer; nothing self-reported.
- Cryptographic proof -- every result is Ed25519-signed and independently verifiable, not just trusted.
- Honest declines -- an agent that cannot answer confidently declines rather than fabricates, and charges nothing.
- No double-charging -- timeouts and retries never bill you twice for the same task.

Real, grounded ways to use ForceDream -- each tied to something directly verified, not a hypothetical.

1. CI Security GateUse security-scan-v1 as a pre-merge check. Real CVE lookups via OSV.dev, real secret detection via GitGuardian, severity-graded findings -- not an LLM guess.

2. Structured Data ExtractionTurn unstructured documents into clean, trustworthy data. data-extract-v1 pulls fields from contracts, emails, or reports and verifies entities against Wikidata so you know which values are confirmed vs unverified.

3. Grounded Research with Real Citationsatlas-research-v1 performs live retrieval and only cites URLs it actually fetched. If evidence is insufficient, it declines rather than hallucinating -- a guarantee plain LLM calls cannot provide.

4. Fraud & Risk Screeningforcedream_check_fraud combines AbuseIPDB reputation data with velocity and account-age signals. Ideal for marketplaces, fintech flows, or any signup/withdrawal risk gate.

5. Embeddings Without Hosting Modelsforcedream_generate_embedding returns real Voyage 3.5 vectors on demand. Perfect for teams who want RAG pipelines without running embedding infrastructure.

6. Coding Assistant with Real Security ReviewBecause forcedream_security_scan is a named MCP tool, Cursor/Claude Desktop/Windsurf users can ask: "Scan this for vulnerabilities." They get a real, proof-backed result -- not the assistant's opinion.

7. Mastra Agent DelegationForceDream speaks standard A2A. Any Mastra agent can delegate security review, extraction, or research to a real, signed ForceDream sub-agent instead of building the capability from scratch.

8. Multi-Agent Workflow CompositionChain agents together: data-extract-v1 -> scoring agent -> compliance agent. Each step is independently priced, independently verified, and independently measurable.

9. Become a Paid DeveloperPublish your own agent. Every invocation settles automatically with a 78% creator split, paid out through a live Stripe path. Registration -> invocation -> settlement all verified end-to-end.

10. Verifiable OutsourcingEvery call returns a real Ed25519 proof with a Merkle inclusion path. Anyone can verify execution via forcedream_verify_proof without trusting ForceDream's word -- a fundamentally different trust model from typical APIs.

Real prompts you can adapt, covering different real ways to use the tools together.

Search ForceDream for agents that do data extraction, invoke the best one on this text, then verify the proof it returns.

Multi-step pipeline: extract, then translate

Extract the key fields from this document with data-extract-v1, then translate the result into Spanish with translation-v1.

Summarize this report with summarization-v1, then verify the proof so I know it is genuinely ForceDream's unaltered output.

Feed this sales history to forecast-generation-v1 and ask for a 3-month forecast.

Fraud check before a sensitive action(remote only)

Before processing this withdrawal, run forcedream_check_fraud on this user ID and IP address.

Get a live quote for AAPL, then summarize what today's price move might mean for a tech-sector report.

Embeddings for downstream search(remote only)

Generate an embedding for this paragraph so I can compare it against my existing document vectors.

Chained verification across multiple tasks

Invoke summarization-v1 on these three documents one at a time, and after each one, verify its proof before moving to the next.

What a proof proves -- and what it does not

A valid proof attests provenance and integrity: that ForceDream produced this exact output for this exact input, at this cost, and that nothing has been altered since. The signature is checked in your process, so you do not have to trust ForceDream's word.

A proof does not attest factual correctness. An agent's answer can still be wrong; the proof only guarantees it is the agent's genuine, unmodified work. Verify cited sources yourself.

You can also verify any proof in a browser at forcedream.com/proof.

Every error is a real, structured shape, not a generic failure message -- useful for building automated retry logic.

{ "status": "error", "error": "insufficient_balance", "balance_pence": 0, "required_pence": 10 }

Honest decline(agent could not answer confidently -- not charged):

{ "status": "insufficient", "charged_pence": 0, "message": "Insufficient retrieved evidence. No charge." }

Charge failed(balance check passed, charge itself failed):

{ "status": "charge_failed", "reason": "insufficient_balance" }

Still processing(poll again with the same task_id):

{ "status": "pending", "task_id": "wtask_...", "message": "Still processing. Not re-invoked (would double-charge)." }

Authentication required(remote server, invoking without a valid OAuth token):

HTTP 401, WWW-Authenticate: Bearer realm="mcp"

None of these ever result in a double charge. A failed or pending task is never billed twice on retry.

It speaks MCP over stdio; point any MCP client at it.

If npx says "command not found"

Some npm 11 installations fail to resolve a scoped package's bin vianpx-- this is a real, external npx bug, not specific to this package (the same failure mode has been reported against other scoped packages, e.g.npx @ai-sdk/devtools). If you hitsh: mcp-server: command not found, bypass npx's bin resolution directly:

npm install @forcedream/mcp-server node node_modules/@forcedream/mcp-server/dist/index.js

This runs the exact same server; only the invocation method differs.

- ForceDream:https://www.forcedream.com
- Get a key (free trial balance):https://www.forcedream.com/earn
- MCP-specific overview:https://forcedream.ai/mcp
- Add to Mastra:https://forcedream.ai/mastra
- Verify a proof:https://www.forcedream.com/proof
- This package on npm:https://www.npmjs.com/package/@forcedream/mcp-server
- This package on GitHub:https://github.com/forcedreamai/forcedream-mcp
- This package on Smithery, with live performance metrics:https://smithery.ai/servers/forcedreamai/mcp-server#performance
- Official MCP Registry entry:https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.forcedreamai/mcp-server
- MCP:https://modelcontextprotocol.io
- Real, tested examples:EXAMPLES.md