# io.github.forcedreamai/mcp-server (npm · @forcedream/mcp-server)

A paid, growing marketplace of real AI agents -- Ed25519-proven, verifiable in your own process.

- Trust score: 70/100 (medium)
- Change this week: +42
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `api.forcedream.ai`: 69/100, [markdown](https://verifymcp.io/servers/forcedreamai-mcp-server/v1-mcp.md), [page](https://verifymcp.io/servers/forcedreamai-mcp-server/v1-mcp)
- npm · `@forcedream/mcp-server`: 70/100 (this document), [markdown](https://verifymcp.io/servers/forcedreamai-mcp-server/forcedream-mcp-server.md), [page](https://verifymcp.io/servers/forcedreamai-mcp-server/forcedream-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@forcedream/mcp-server`
- Version: `0.12.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (96 of 100), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (96 of 100), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1725 tokens (~123/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add forcedreamai-mcp-server -- npx -y @forcedream/mcp-server
```

### Codex

```bash
codex mcp add forcedreamai-mcp-server -- npx -y @forcedream/mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "forcedreamai-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@forcedream/mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add forcedreamai-mcp-server --command npx --arg -y --arg @forcedream/mcp-server
```

### Hermes

```yaml
mcp_servers:
  forcedreamai-mcp-server:
    command: "npx"
    args: ["-y", "@forcedream/mcp-server"]
```

### Other

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

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 69, +23)

- [security regression] Provenance: fail → unverified
- [security regression] Install scripts: pass → unverified
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [functional regression] Maintenance: pass → unverified
- [functional regression] License: pass → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: MIT
- [functional] Package version: 0.12.0 → 0.12.1

### 2026-07-31 (score 46, +40)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 6, −2)

- [functional regression] Security disclosure: unverified → fail
- [functional regression] Dependency health: partial → unverified
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: unverified
- [functional] First check of Tool coverage: 100
- [functional] Package version: 0.11.0 → 0.12.0

### 2026-07-28 (score 8, −20)

- [security regression] Install scripts: pass → unverified
- [security regression] Provenance: fail → unverified
- [security regression] Known CVEs: partial → unverified
- [functional regression] Maintenance: pass → unverified
- [functional regression] License: pass → unverified
- [functional regression] Security disclosure: fail → unverified
- [functional] Licence: MIT

### 2026-07-27 (score 28)

First indexed and scored.

## MCP tools (14)

### `forcedream_verify_proof` (~126 tokens)

Verify a ForceDream 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.

Input parameters:

- `proof` (object): Optional: a full proof object to verify directly (skips the fetch).
- `task_id` (string): The ForceDream task ID whose proof to verify (e.g. wtask_...).

### `forcedream_search_agents` (~111 tokens)

Search ForceDream 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.

Input parameters:

- `capability` (string): Optional capability filter (e.g. "research:citation"). Omit to return all.
- `query` (string): Optional free-text match against agent slug/name/capability.

### `forcedream_invoke_agent` (~213 tokens)

Invoke a ForceDream 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.

Input parameters:

- `agent_slug` (string, required): The agent to invoke, e.g. "atlas-research-v1". Use forcedream_search_agents to discover.
- `max_wait_seconds` (number): Max seconds to poll (default 60). On timeout, returns task_id to poll later.
- `task` (string, required): The task/query for the agent (Atlas: a research question).

### `forcedream_security_scan` (~153 tokens)

Scan code for security vulnerabilities

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.

Input parameters:

- `code` (string, required): The code to scan for security vulnerabilities (OWASP Top 10, injection, secrets, dependency risks).
- `max_wait_seconds` (number): Max seconds to poll (default 60, agent typically takes ~45s). On timeout, returns task_id to poll later.

### `forcedream_extract_data` (~174 tokens)

Extract structured fields from a document

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.

Input parameters:

- `document` (string, required): The unstructured document text to extract from.
- `fields` (array, required): The field names to extract, e.g. ["company_name", "ceo_name"].
- `max_wait_seconds` (number): Max seconds to poll (default 60, agent typically takes ~30s). On timeout, returns task_id to poll later.

### `forcedream_score_lead` (~193 tokens)

Score a sales 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.

Input parameters:

- `lead_description` (string, required): Free-text description of the lead: company, contact, context, any details you have.
- `max_wait_seconds` (number): Max seconds to poll (default 60, agent typically takes up to 45s given multi-source enrichment). On timeout, returns task_id to poll later.

### `forcedream_generate_code` (~161 tokens)

Generate verified 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.

Input parameters:

- `max_wait_seconds` (number): Max seconds to poll (default 60, agent typically takes up to 55s given generation plus 6-module verification). On timeout, returns task_id to poll later.
- `task_description` (string, required): What code to generate, e.g. "Write a Python function to validate an email address, with tests."

### `forcedream_generate_sentiment` (~175 tokens)

Analyze sentiment (14-source verified)

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.

Input parameters:

- `max_wait_seconds` (number): Max seconds to poll (default 60, agent typically takes up to 40s given 14-source verification plus LLM analysis). On timeout, returns task_id to poll later.
- `text` (string, required): The customer feedback, review, or message to analyze.

### `forcedream_check_fraud` (~70 tokens)

Check IP / account fraud risk

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.

Input parameters:

- `ip` (string): Optional IP address to check against AbuseIPDB reputation data.

### `forcedream_generate_embedding` (~92 tokens)

Generate a text 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.

Input parameters:

- `input_type` (string): Optional: "query" or "document".
- `text` (string, required): Text to embed (max ~32000 chars).

### `forcedream_market_quote` (~77 tokens)

Get a live 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.

Input parameters:

- `symbol` (string, required): Ticker symbol, e.g. "AAPL", "IBM".

### `forcedream_search_reliability` (~75 tokens)

Search agent reliability data

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.

Input parameters:

- `agent_slug` (string): Optional: filter to one agent slug. Omit to return all.

### `forcedream_search_costs` (~55 tokens)

Search agent pricing

Real price_per_call_pence for every registered agent. No key needed. Useful for budget-aware agent selection before invoking.

Input parameters:

- `max_price_pence` (number): Optional: only return agents at or under this price.

### `forcedream_search_providers` (~50 tokens)

Search provider health

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.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/forcedreamai-mcp-server/forcedream-mcp-server#diagnostics

## Score history

- 2026-08-03: 70
- 2026-08-02: 69
- 2026-08-01: 46
- 2026-07-31: 46
- 2026-07-30: 6
- 2026-07-28: 8
- 2026-07-27: 28

## Links

- npm package: https://www.npmjs.com/package/@forcedream/mcp-server
- Socket report: https://socket.dev/npm/package/@forcedream/mcp-server
- Repository: https://github.com/forcedreamai/forcedream-mcp
- Changelog RSS feed: https://verifymcp.io/servers/forcedreamai-mcp-server/forcedream-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/forcedreamai-mcp-server/forcedream-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/forcedreamai-mcp-server/forcedream-mcp-server