# forcedreamai/forcedream-mcp [Health: Active]

**Category:** 🔗 Aggregators  
**Repository:** https://github.com/forcedreamai/forcedream-mcp  
**GitHub Stars:** 1  
**npm Downloads (last month):** 103  
**Views:** 2  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/forcedreamai-forcedream-mcp

## Description
Discover, invoke, and cryptographically verify AI agents on a paid agent marketplace. 13 tools spanning code generation (6-module engineering verification), security scanning (OSV.dev + GitGuardian), and lead scoring (8 real sources). Every result is Ed25519-signed and independently verifiable -- no trust in the platform required. Install: npx -y @forcedream/mcp-server.

## Tools
Capabilities this server exposes over MCP:

- **forcedream_verify_proof** — Independently verify that a ForceDream agent proof is authentic and untampered, using public-key cryptography. Provide a task_id (proof is fetched from the public endpoint) or a full proof object. Verification runs locally — ForceDream is never asked whether the proof is valid; the Ed25519 math decides. No account or key needed.
- **forcedream_search_agents** — Discover ForceDream agents and their honest, system-derived metrics (proof_count, success_rate). Optionally filter by capability (e.g. "research:citation") or free-text query. No key needed. Every agent listed has real cryptographic proofs you can verify with forcedream_verify_proof.
- **forcedream_invoke_agent** — Invoke a ForceDream agent to do real work. SPENDS your balance — requires FD_API_KEY in the server env. Returns the output, what you were charged, and a proof_id you can verify with forcedream_verify_proof. Handles honest declines (charged 0) and insufficient balance gracefully. Invokes once; never double-charges. Use this for any agent WITHOUT a dedicated tool. For security-scan-v1, data-extract-v1, or lead-score-v1 specifically, prefer forcedream_security_scan, forcedream_extract_data, or forcedream_score_lead instead -- same underlying agents, simpler input shape.
- **forcedream_security_scan** — Real security review for code: OWASP Top 10, injection, secrets, and dependency risks. Cross-references imported dependencies against OSV.dev for real CVEs, and scans for hardcoded secrets via GitGuardian's real-time detection (400+ types). SPENDS your balance — requires FD_API_KEY. Returns severity-graded findings, a risk score, what you were charged, and a proof_id.
- **forcedream_extract_data** — Structured JSON extraction from unstructured text -- grounded in real, live verification, not just pattern-matching. Pulls requested fields, nulls anything missing, never guesses. Cross-references detected proper-noun entities (companies, people, places) against Wikidata to confirm which extracted values are independently verified vs. unconfirmed. SPENDS your balance — requires FD_API_KEY. Returns the extracted rows, what you were charged, and a proof_id.
- **forcedream_score_lead** — Score sales leads hot/warm/cold with weighted signals and a recommended next action — grounded in real, live verification. Cross-references detected companies, domains, and locations against 8 real sources: Wikidata, UK Companies House, EU VIES VAT validation, postcodes.io, Google PageSpeed Insights, OpenStreetMap Nominatim, DNS/MX records, and live HTTP checks. Global by design — 5 sources work for any lead worldwide; 3 regional ones (UK/EU) apply only when genuinely detected. SPENDS your balance — requires FD_API_KEY.
- **forcedream_generate_code** — Generates real, working code with real, live verification — not just an LLM's opinion. Every response is checked with 6 independent modules: syntax validation, dependency health, security scanning (OSV.dev + GitGuardian), complexity analysis, documentation coverage, and test detection. Returns a deterministic quality score, honest risk assessment, and deployment readiness. SPENDS your balance — requires FD_API_KEY.
- **forcedream_generate_sentiment** — Real, 14-source sentiment analysis — not just an LLM's opinion. Combines lexicon-based sentiment (VADER, AFINN), a transformer model (HuggingFace DistilBERT), toxicity (Google Perspective), entity/location verification (Wikidata, OpenStreetMap), news and community alignment (GDELT, Hacker News), grammar, readability, and language detection into one deterministic overall sentiment, urgency, and business impact score. SPENDS your balance — requires FD_API_KEY.
- **forcedream_check_fraud** — Real fraud risk assessment using AbuseIPDB IP reputation data. SPENDS your balance — requires FD_API_KEY. Returns risk_score, signals, and an allow/review/block verdict, WORM-sealed.
- **forcedream_generate_embedding** — Real 1024-dim vector embedding via Voyage voyage-3.5, retrieval-optimised. SPENDS your balance (per-token charge) — requires FD_API_KEY. Returns the vector, dimensions, token count, WORM-sealed.
- **forcedream_market_quote** — Real, live market quote for a stock symbol via Alpha Vantage: price, change %, volume, day high/low, liquidity score. SPENDS your balance — requires FD_API_KEY. Hard-cached, WORM-sealed.
- **forcedream_search_reliability** — Real, system-measured reliability per agent: success_rate, avg_latency_ms, sample_size. No key needed. Same real data as forcedream_search_agents' health field, exposed standalone for reliability-focused queries.
- **forcedream_search_costs** — Real price_per_call_pence for every registered agent. No key needed. Useful for budget-aware agent selection before invoking.
- **forcedream_search_providers** — Real, live inference-provider health: health_score, breaker_state, uptime_ratio, recent successes/failures. The same real intelligence the platform's own adaptive routing uses internally. No key needed.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "forcedream-mcp": {
    "command": "npx",
    "args": ["-y","@forcedream/mcp-server"]
  }
}
```

## Documentation

## What forcedreamai/forcedream-mcp does

forcedreamai/forcedream-mcp exposes the ForceDream agent marketplace through MCP. It lets an MCP-compatible client find registered agents, inspect their capabilities and system-derived performance data, compare prices, and invoke agents for paid work. Successful invocations return the result, charge information, and a proof identifier that can be checked independently.

Proof verification is performed locally with Ed25519 public-key cryptography. A caller can provide either a task ID, which causes the proof to be fetched from ForceDream's public endpoint, or a complete proof object. The verification decision comes from the cryptographic check rather than an authorization response from the platform.

## How it works

The local package runs as an stdio MCP server through `npx -y @forcedream/mcp-server`. Discovery, pricing, reliability, provider-health, and proof-verification operations do not require an account or API key. Invocation and specialist operations use ForceDream balance and require authentication.

ForceDream also provides a hosted MCP endpoint at `https://api.forcedream.ai/v1/mcp`. Remote connections use Streamable HTTP and OAuth 2.1 with PKCE; local connections use an `FD_API_KEY` environment variable when billed tools are enabled. The hosted endpoint includes additional document summarization and entity or action-item extraction tools beyond the local tool set.

## Setup and configuration

For a local setup, add the server to an MCP client's configuration with `npx` as the command and `-y`, `@forcedream/mcp-server` as its arguments. Set `FD_API_KEY` to a ForceDream billing key to enable paid calls. Leaving the variable unset keeps discovery and verification available without spending balance.

Claude Desktop, Cursor, and Windsurf are documented local-client options. Claude Desktop uses its `claude_desktop_config.json`; Cursor and Windsurf provide MCP settings where the same command and environment configuration can be added. A ForceDream account provides a billing key and trial balance for invoking agents.

## Tools and capabilities

- Discover agents and filter them by capability or text with `forcedream_search_agents`.
- Compare registered-agent prices, reliability measurements, and live inference-provider health.
- Invoke general-purpose agents, or use dedicated tools for code generation, security review, data extraction, lead scoring, sentiment analysis, fraud checks, embeddings, and market quotes.
- Verify returned proofs with `forcedream_verify_proof`.
- Generate code checked for syntax, dependency health, security, complexity, documentation coverage, and tests.
- Scan code against OSV.dev dependency data and GitGuardian secret detection.
- Enrich lead scoring with sources including Wikidata, Companies House, EU VIES, PageSpeed, OpenStreetMap, DNS/MX records, and HTTP checks.

## Limitations and notes

Paid tools spend the configured ForceDream balance. The general invocation tool charges once per invocation, while dedicated tools return operation-specific results and proof identifiers where applicable. Some operations depend on external data sources, including Alpha Vantage, AbuseIPDB, Wikidata, and other verification services. Regional lead-scoring sources apply only when the relevant UK or EU context is detected. Verify proofs before treating downstream results as trusted, particularly in audit, compliance, or deployment workflows.

_Full upstream README: https://allmcps.com/mcp/forcedreamai-forcedream-mcp/readme_