mallory-grapher
Provides a headless session runtime for reactive compute graphs, enabling MCP-driven cell operations without a DOM or browser.
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.tsin mallory-graph, ~500 lines) has no structural blocker to running headless — proven empirically, not just asserted.- Most panels'
useXGraph()seed step readswindow.location.hash/getComputedStylefor URL-state hydration and theming. Both are already guarded withtypeof 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_savetool (#163 item 1, shipped) is gated OFF by default behind an explicit env var (MALLORY_GRAPH_ENABLE_MCP_WRITE=1), mirroringllmtm'sLLMTM_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).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.