mallory-grapher

mallory-grapher

Provides a headless session runtime for reactive compute graphs, enabling MCP-driven cell operations without a DOM or browser.

Category
访问服务器

README

mallory-grapher

A headless, DOM-less session runtime for the mallory family's reactive compute graph (CellGraph), agent-drivable over MCP.

Why this exists

mallory-graph's in-page WebMCP tools (useCellGraphTools: ${prefix}_list_cells/get_cell/set_cell) already let an agent drive a live, reactive CellGraph — but only from inside a rendered browser tab. The server-side MCP endpoint mallory-graph ships today (mallory-mcp, packages/mcp in mallory-plus) only covers stateless math tools (Symbolic eval, guarded tensor/linalg) plus read-only, serialized gallery access (gallery_list/gallery_get read NotebookState.blocks[] JSON — no computed/derived-cell evaluation, no reactivity).

Real session parity — "an agent could run an entire modeling session headlessly" — means running the reactive compute graph itself server-side, with no DOM/React tree at all. That's a materially different, bigger project than either of the above, so it lives here instead of inside mallory-graph.

Split out of mallory-graph#163 after that issue's own audit trail: a feasibility spike (cell-graph-headless-spike.test.ts) already confirmed CellGraph itself has zero window/document references — set/define/get/ subscribe/subscribeAll are plain data-structure + closure code. What doesn't exist yet is the actual session API around it.

Relationship to mallory-graph

Optional, not coupled. mallory-grapher does not depend on mallory-graph, and mallory-graph does not need to depend on mallory-grapher to function. mallory-graph may choose to mount a mallory-grapher-backed MCP route the same way it mounts mallory-mcp today (src/routes/api.mcp.ts) — a separate integration issue, not a prerequisite for this repo to exist or ship v1.

Concretely, this repo owns:

  • The headless session runtime (open a session, drive its cells, read results) — no rendering, no React, no DOM.
  • An MCP tool surface over that runtime.

It deliberately does NOT own:

  • Canvas/WebGL rendering — session parity is about the same get/set/list contract WebMCP already gives an in-page agent, not pixels.
  • mallory-graph's specific panel components, gallery storage, or UI.

What's known so far (carried over from #163's audit)

  • CellGraph's core (cell-graph.ts in mallory-graph, ~500 lines) has no structural blocker to running headless — proven empirically, not just asserted.
  • Most panels' useXGraph() seed step reads window.location.hash / getComputedStyle for URL-state hydration and theming. Both are already guarded with typeof window !== "undefined" checks (existing SSR-safety code), so they degrade gracefully rather than crash — but a real agent-drivable session needs a way to seed state from something other than a browser's URL bar (an MCP tool argument, presumably).
  • Write-path auth precedent: mallory-graph's gallery_save tool (#163 item 1, shipped) is gated OFF by default behind an explicit env var (MALLORY_GRAPH_ENABLE_MCP_WRITE=1), mirroring llmtm's LLMTM_HUB_ENABLE_* convention. A session-runtime write surface should follow the same default-off, explicit-opt-in posture.

Status

v1 implemented. docs/design.md is the settled design; the session runtime, op catalog, MCP tool surface, and both transports are built and tested.

Usage

# stdio (the transport MCP hosts speak natively -- e.g. `claude mcp add`)
npx mallory-grapher

# Streamable HTTP on http://localhost:3920/mcp (or a custom port)
npx mallory-grapher --http
npx mallory-grapher --http 8123

Tools: session_open (kind generic or graph-theory), session_close, session_list, session_set_cell, session_get_cell, session_list_cells, session_define. Computed cells are declared as JSON define-specs over a server-side op catalog (math_eval, graph_parse_edge_list, graph_analyze, graph_bfs/dfs/dijkstra) with {"$cell": "name"} live references — see docs/design.md §5.

Resource guards default modest and are overridable: MALLORY_GRAPHER_MAX_SESSIONS (16), MALLORY_GRAPHER_MAX_CELLS (512), MALLORY_GRAPHER_EVAL_BUDGET_MS (250), MALLORY_GRAPHER_MAX_PAYLOAD_BYTES (262144).

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选