Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

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.

0 this week 75 Trust /100

Last scanned (13 hours ago)

Scores higher than 51% of npm servers

Category AI and Machine Learning

Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security81
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 33 of 103 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency18
  • Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 294 days ago).Pass
  • Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability85
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 885 tokens (~98/item across 9 items; 7 tools + 2 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage94
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 82% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (15)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Nov 26 +1
    • Stability: 0.97 → pass security
  • 18 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 12 Nov 26 +1
    • Stability: 0.97 → pass security
  • 10 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 8 Nov 26 −2
    • Stability: pass → 0.87 functional
  • 2 Nov 26 +1
    • Stability: 0.97 → pass security
  • 1 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 24 Oct 26 −5
    • CVE-2023-54404 affects this package: high ▼ security
    • Known CVEs: pass → fail ▼ security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed npm/@rightnow/forge-mcp-server@1.0.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 1 finding
ID CVE Severity Vector Fix available
GHSA-mrhx-c7xc-m3w5 CVE-2023-54404 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 103 packages
Packages resolved 103
Stale 33
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 7 exposed · ~861 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
forge_auth ~69

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.

NameTypeReqDescription
forceboolean–Force re-authentication even if tokens exist

No output schema declared.

No examples provided.

forge_cancel ~45

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

NameTypeReqDescription
session_idstringyesThe session ID of the job to cancel

No output schema declared.

No examples provided.

forge_credits ~59

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

forge_generate ~217

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.

NameTypeReqDescription
descriptionstringyesDetailed description of what the kernel should do
dtypestring–Data type (float16, float32, bfloat16)
gpustring––
input_shapesarrayyesInput tensor shapes, e.g., [[8, 512, 768]] for a single input
max_iterationsnumber––
operationstringyesOperation name (e.g., "fused_attention", "custom_gelu", "softmax", "matmul")
output_formatstring–Output format
output_shapearray–Expected output tensor shape
target_speedupnumber––
user_promptstring––

No output schema declared.

No examples provided.

forge_optimize ~382

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.

NameTypeReqDescription
gpustring–Target GPU for optimization and benchmarking
kernel_namestringyesShort descriptive name for this kernel (e.g., "flash_attention", "fused_layernorm")
max_iterationsnumber–Maximum optimization iterations. More iterations = higher chance of better speedup.
output_formatstring–Output format. "triton" is recommended (portable, readable). "native_cuda" for maximum control.
pytorch_codestringyesComplete PyTorch code to optimize. Must be a runnable module with a model class.
target_speedupnumber–Target speedup multiplier over torch.compile baseline
user_promptstring–Optional guidance for the optimizer (e.g., "focus on memory bandwidth", "use shared memory tiling")

No output schema declared.

No examples provided.

forge_sessions ~49

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

NameTypeReqDescription
limitnumber–Number of sessions to return
statusstring–Filter by session status

No output schema declared.

No examples provided.

forge_status ~40

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

NameTypeReqDescription
session_idstringyesThe session ID returned from forge_optimize or forge_generate

No output schema declared.

No examples provided.

Install

How do I install the io.github.RightNow-AI/forge-mcp-server server?

io.github.RightNow-AI/forge-mcp-server runs locally as an npm package, launched with npx -y @rightnow/forge-mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @rightnow/forge-mcp-server

# add to Claude Code
claude mcp add rightnow-ai-forge-mcp-server -- npx -y @rightnow/forge-mcp-server
Common questions

What is the io.github.RightNow-AI/forge-mcp-server server?

io.github.RightNow-AI/forge-mcp-server is listed in the public MCP registry as io.github.RightNow-AI/forge-mcp-server. Turn PyTorch into fast CUDA/Triton kernels on real datacenter GPUs with up to 14x speedup. This page covers its npm package (@rightnow/forge-mcp-server).

Is the io.github.RightNow-AI/forge-mcp-server server safe to use?

io.github.RightNow-AI/forge-mcp-server scores 75 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.RightNow-AI/forge-mcp-server server expose?

io.github.RightNow-AI/forge-mcp-server exposes 7 tools: forge_auth, forge_credits, forge_optimize, forge_generate, forge_status, and 2 more. Their descriptions and schemas cost roughly 861 tokens of context every time the server is loaded.

Is the io.github.RightNow-AI/forge-mcp-server server still maintained?

io.github.RightNow-AI/forge-mcp-server is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.RightNow-AI/forge-mcp-server server under?

io.github.RightNow-AI/forge-mcp-server declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the io.github.RightNow-AI/forge-mcp-server server?

VerifyMCP ran 15 checks on io.github.RightNow-AI/forge-mcp-server, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about io.github.RightNow-AI/forge-mcp-server: Security disclosure. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.