# io.github.RightNow-AI/forge-mcp-server (npm · @rightnow/forge-mcp-server)

Turn PyTorch into fast CUDA/Triton kernels on real datacenter GPUs with up to 14x speedup.

- Trust score: 65/100 (medium)
- Change this week: +19
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@rightnow/forge-mcp-server`: 65/100 (this document), [markdown](https://verifymcp.io/servers/rightnow-ai-forge-mcp-server/rightnow-forge-mcp-server.md), [page](https://verifymcp.io/servers/rightnow-ai-forge-mcp-server/rightnow-forge-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@rightnow/forge-mcp-server`
- Version: `1.0.2`
- 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 (105 of 109), 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 (105 of 109), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 184 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 84/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 885 tokens (~98/item across 9 items; 7 tools + 2 resources), lean.
  - 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**: 94/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 82% 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 rightnow-ai-forge-mcp-server -- npx -y @rightnow/forge-mcp-server
```

### Codex

```bash
codex mcp add rightnow-ai-forge-mcp-server -- npx -y @rightnow/forge-mcp-server
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add rightnow-ai-forge-mcp-server --command npx --arg -y --arg @rightnow/forge-mcp-server
```

### Hermes

```yaml
mcp_servers:
  rightnow-ai-forge-mcp-server:
    command: "npx"
    args: ["-y", "@rightnow/forge-mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "rightnow-ai-forge-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@rightnow/forge-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 65, −3)

No change was recorded against any check on this day. Supply Chain Security went from 97 to 87. Other categories moved too: Stability & Change Management rose 4.

### 2026-08-02 (score 68, +19)

- [security improvement] Malware scan: unverified → pass
- [functional improvement] Stability: unverified → 0.23

### 2026-08-01 (score 49, +29)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: MIT

### 2026-07-31 (score 20, −8)

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

### 2026-07-30 (score 28, +10)

- [security regression] Malware scan: pass → unverified
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 100

### 2026-07-28 (score 18, −28)

- [functional regression] Schema quality: 100 → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (7)

### `forge_auth` (~69 tokens)

Authenticate with Forge

Authenticate with the RightNow Forge GPU kernel optimization service.
Opens the user's browser to sign in via the RightNow dashboard. Required before using any other Forge tools.
If valid tokens already exist, verifies them without opening the browser.

Input parameters:

- `force` (boolean): Force re-authentication even if tokens exist

### `forge_credits` (~59 tokens)

Check Forge Credits

Check your current Forge credit balance. Each single-GPU optimization costs 1 credit.
Credits are only charged for successful optimizations (speedup >= 1.1x).
Credits are lifetime (not monthly) and can be purchased on the dashboard.

### `forge_optimize` (~382 tokens)

Optimize GPU Kernel

Submit PyTorch code to Forge for GPU kernel optimization.
Forge generates optimized Triton or CUDA kernels, evaluates them on real H100/A100 GPUs,
and returns the best result with speedup metrics over torch.compile(max-autotune).

USE THIS TOOL WHEN YOU SEE:
\- PyTorch custom operations (torch.autograd.Function, custom forward/backward)
\- Manual CUDA kernels that could be faster
\- Performance-critical tensor operations (attention, convolution, normalization, softmax)
\- Code with comments like "slow", "bottleneck", "optimize", "performance"
\- torch.compile() targets or triton.jit kernels
\- Any nn.Module with significant compute in forward()
\- Matrix multiplication, reduction, or scan operations
\- Custom loss functions with reduction operations
\- Fused operation opportunities (e.g., LayerNorm + activation)

The tool streams real-time progress and blocks until optimization completes (1-10 minutes).
Cost: 1 credit per optimization (only charged if speedup >= 1.1x).
Requires authentication via forge_auth first.

Input parameters:

- `gpu` (string): Target GPU for optimization and benchmarking
- `kernel_name` (string, required): Short descriptive name for this kernel (e.g., "flash_attention", "fused_layernorm")
- `max_iterations` (number): Maximum optimization iterations. More iterations = higher chance of better speedup.
- `output_format` (string): Output format. "triton" is recommended (portable, readable). "native_cuda" for maximum control.
- `pytorch_code` (string, required): Complete PyTorch code to optimize. Must be a runnable module with a model class.
- `target_speedup` (number): Target speedup multiplier over torch.compile baseline
- `user_prompt` (string): Optional guidance for the optimizer (e.g., "focus on memory bandwidth", "use shared memory tiling")

### `forge_generate` (~217 tokens)

Generate GPU Kernel

Generate an optimized GPU kernel from scratch based on a specification.
Use this when you need to create a new high-performance kernel without existing PyTorch code.
Forge will generate a PyTorch baseline first, then optimize it into Triton or CUDA.

Requires authentication via forge_auth first. Cost: 1 credit per generation.

Input parameters:

- `description` (string, required): Detailed description of what the kernel should do
- `dtype` (string): Data type (float16, float32, bfloat16)
- `gpu` (string)
- `input_shapes` (array, required): Input tensor shapes, e.g., [[8, 512, 768]] for a single input
- `max_iterations` (number)
- `operation` (string, required): Operation name (e.g., "fused_attention", "custom_gelu", "softmax", "matmul")
- `output_format` (string): Output format
- `output_shape` (array): Expected output tensor shape
- `target_speedup` (number)
- `user_prompt` (string)

### `forge_status` (~40 tokens)

Check Optimization Status

Check the current status of a running or completed Forge optimization job.

Input parameters:

- `session_id` (string, required): The session ID returned from forge_optimize or forge_generate

### `forge_cancel` (~45 tokens)

Cancel Optimization

Cancel a running Forge optimization job. Credits may be refunded if less than 20% of iterations completed.

Input parameters:

- `session_id` (string, required): The session ID of the job to cancel

### `forge_sessions` (~49 tokens)

List Optimization Sessions

List past Forge optimization sessions with their results. Useful for checking what has already been optimized.

Input parameters:

- `limit` (number): Number of sessions to return
- `status` (string): Filter by session status

## Diagnostics

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

## Score history

- 2026-08-03: 65
- 2026-08-02: 68
- 2026-08-01: 49
- 2026-07-31: 20
- 2026-07-30: 28
- 2026-07-28: 18
- 2026-07-27: 46

## Links

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