Forge

MCP文档知识

提供方 VoxellInc · 包名 @voxell/forge-mcp

文档知识 stdio · 本地进程 OAuth 授权 社区 / 第三方 Claude DesktopClaudeCursorVS Code
查看接入方式

Forge is Voxell's hosted text-embedding API. This MCP server exposes two tools — embed (turn text into vectors) and list_models — so any MCP-compatible agent can generate embeddings for semantic search, RAG, clustering, and dedup.

一句话选型结论

按资料字段整理

Forge 属于文档知识类 MCP 服务器,stdio · 本地进程,OAuth 授权,可直接接入 Claude Desktop、Claude、Cursor 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类文档知识 传输方式stdio · 本地进程 鉴权OAuth 授权 部署方式本地部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

文档知识
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

embeddings vector semantic search rag retrieval vector search nlp

支持客户端

适用场景

embeddingsvectorsemantic search

安装与配置

stdio · 本地进程 OAuth 授权
客户端在本机拉起子进程,数据不出本机
npx -y @voxell/forge-mcp

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Cross-platform,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
文档检索问答

在你的文档库里按问题找答案。

知识库读写

把新资料写进知识库,随用随取。

内容整理

把零散资料归纳成结构化笔记。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude Desktop、Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 使用前要准备好OAuth 授权对应的凭据,并按最小权限配置。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在文档知识场景里让模型直接调用外部能力的人。
  • 已经在用 Claude Desktop、Claude 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Forge当前 未标注 stdio · 本地进程 本地部署 有 未标注
dify 未标注 stdio · 本地进程 本地部署 有 2026-04-11
open-webui 未标注 stdio · 本地进程 本地部署 有 2026-04-11
JeecgBoot 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Cherry Studio 未标注 未标注 未标注 无 2026-05-17
mempalace 未标注 stdio · 本地进程 本地部署 有 2026-04-11

服务器档案

文档知识
字段来自项目仓库与公开索引,中文说明由本站标注
提供方VoxellInc上游标注的维护方 VoxellInc
分类文档知识本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式OAuth 授权远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时@voxell/forge-mcp · Cross-platform本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

6.8 KB
来自项目仓库与上游目录的原文,未做删改

@voxell/forge-mcp

An MCP server for Forge — Voxell's hosted text-embedding API. It exposes Forge to any
MCP client (Claude, Cursor, Cline, Windsurf, VS Code, …) as two tools:

  • embed — turn text into vectors
  • list_models — list available models and their dimensions

You bring a Forge API key. The server is stateless, and Voxell does not store the text you
send or the vectors it returns
— only usage metadata (token counts) is recorded, for billing.
It does embeddings only — no storage, no search, no RAG. Those are different products.

Quick install

One-click install in your editor (then replace your-key-here with a real key from
dash.voxell.ai):

Claude Code — one command:```bash
claude mcp add forge -e FORGE_API_KEY=your-key-here -- npx -y @voxell/forge-mcp


Any other client (Claude Desktop, Cline, Windsurf, Zed, …) uses the standard `mcpServers`
block — see Use it below.

## Why Forge

- **Quality you can dial.** Three tiers: `turbo` (1024d, fast, the default), `pro` (2560d) and
  `ultra` (4096d, highest quality). Pick your point on the quality and cost curve.
- **Benchmark-leading.** Voxell's Ingot-8B-R3 ranks #1 for English on the public MTEB leaderboard
  (English v2), with a 75.98 mean task score across 41 tasks: the top usable English embedding
  model. See the model card.
- **Measured on public documents.** Voxell's retrieval pipeline, built on Forge, is measured on
  four public corpora (7,817 documents, 980,885 passages). On 800 model-written questions, which
  are easier than a test set written by people, the first result answers the question for 83%.
  Method and limits: Measured retrieval.
- **Matryoshka (MRL).** Set `dim` to truncate (re-normalized) for ~4× smaller, cheaper vectors.
- **Low latency** (Go + CUDA engine), **zero-trust** (per-key auth; mTLS available), and **free to
  start** (`turbo` is free forever, no card: dash.voxell.ai; more at
  voxell.ai/forge).

## Measured retrieval

This server returns vectors only. Voxell also runs a retrieval pipeline built on Forge, and
publishes what it measures on documents anyone can read.

Four public corpora, 7,817 documents and 980,885 passages in total, 800 questions (200 per
corpus), measured 2026-10-05:

| corpus | documents | first result answers the question | one of the top three answers it |
|--------|-----------|-----------------------------------|---------------------------------|
| SEC filings | 2,010 | 91% | 95% |
| USPTO patents | 4,008 | 86.5% | 91.5% |
| NASA technical reports | 1,210 | 67% | 78% |
| arXiv technical papers | 589 | 86.5% | 96% |
| all four | 7,817 | 83% | 90% |

The right document is in the top ten for 95% of the questions.

Read these numbers for what they are. The questions were written by a model from the documents
and judged against the passage text, which is easier than a test set written by people. The
numbers describe what this pipeline does on these corpora. They are not a comparison with any
other vendor, and they are not what the `embed` tool does on its own: the pipeline adds the steps
the receipts list, such as a cross-encoder reranker, a one-line document identity in every
passage, and routing to the documents a question names. Each receipt is published with a fixed
sample of its questions, misses included: voxell.ai/retrieval.

## What you can do with it

- **Add semantic search** — embed your documents with `input_type: "document"` and each query
  with `input_type: "query"`, then rank by cosine similarity.
- **Build RAG** — embed a knowledge base, store the vectors, and retrieve the closest chunks to
  ground an LLM.
- **Find similar or duplicate text** — embed two texts and compare their vectors.
- **Cluster or classify** — embed a batch, then cluster or train a classifier on the vectors.
- **Shrink vector storage** — set `dim` to truncate (Matryoshka) and trade a little accuracy
  for smaller, cheaper vectors.
- **Straight from your editor** — ask your AI agent (Cursor, Claude, …) to embed a snippet, a
  batch, or a file via the `embed` tool — no separate script.

## Requirements

- Node.js ≥ 18 (tested on 20)
- A Forge API key — create one at https://dash.voxell.ai. `turbo` is free forever, no card.

## Use it

Most MCP clients run it on demand with `npx`. Add this to your client's MCP config:```json
{
  "mcpServers": {
    "forge": {
      "command": "npx",
      "args": ["-y", "@voxell/forge-mcp"],
      "env": { "FORGE_API_KEY": "your-key-here" }
    }
  }
}

(Cursor, Claude Desktop, Cline, Windsurf, and VS Code all use this mcpServers shape.)

Tools

embed

arg · type · default · notes
input · string or string[] · — · text(s) to embed (required)
model · string · turbo · turbo (1024-d), pro (2560-d), ultra (4096-d)
dim · number · model default · truncate to N dimensions (Matryoshka) — works on every model
input_type · "query" \ · "document" · document · use query for search queries

Returns the vectors plus the model, dimension, and token count.

Default is turbo — the one you probably want. pro/ultra trade size and speed for more
dimensions.

list_models

Lists the available models and their dimensions.

Configuration

env required default
FORGE_API_KEY yes —
FORGE_BASE_URL no https://api.voxell.ai

Beyond MCP: OpenAI-compatible API

Forge speaks the OpenAI embeddings API. Point any OpenAI client at Forge — no code change,
and your existing vector dimensions are preserved:```python
from openai import OpenAI

client = OpenAI(base_url="https://api.voxell.ai/v1", api_key="your-forge-key")

the exact call you already make — now on a higher-ranked engine:

client.embeddings.create(model="text-embedding-3-large", input=["hello world"]) # -> 3072-d
```

Your OpenAI model names map to a matching-dimension Forge tier (text-embedding-3-small/
ada-002 → 1536-d, text-embedding-3-large → 3072-d), so existing vector stores slot in
unchanged. Or address Forge tiers directly — turbo · pro · ultra. Also supports dimensions
(Matryoshka, re-normalized) and encoding_format: "base64".

It's an upgrade on every path. Forge's smallest tier (turbo) outranks OpenAI's
largest embedding model (text-embedding-3-large) on MTEB, so there's no drop-in that lands
worse. And Voxell's Ingot-8B-R3 ranks #1 for English on the public MTEB leaderboard: a different
league.

Why re-embedding onto Forge is worth it. Embedding is a one-way door: whatever an encoder
discards at write time is gone — no reranker, longer prompt, or bigger LLM downstream reconstructs
what the vectors never captured. The model you embed with sets the ceiling on everything above it.
Re-embed once onto a higher-ranked engine and that ceiling rises — permanently.

License

MIT © Voxell, Inc.

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Forge 怎么安装?

在客户端按下面的安装命令接入:npx -y @voxell/forge-mcp。对应的包名是 @voxell/forge-mcp。装完在客户端配置里引用同一个包或端点。

Forge 怎么在 Claude Desktop、Claude、Cursor 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Forge 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Forge 需要 API Key 吗?

资料标注需要OAuth 授权认证,使用前准备好对应凭据,并按最小权限配置。

Forge 支持哪些客户端?

资料标注支持 Claude Desktop、Claude、Cursor、VS Code、Windsurf、Cline;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Forge 能提供哪些能力?

资料显示能力标签包括 embeddings、vector、semantic search、rag、retrieval、vector search。具体工具清单以官方文档为准。

Forge 需要什么运行环境?

运行时为 Cross-platform;属于本地进程,需要在本机装好运行环境。

Forge 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。