HyperWeave MCP server
Commit Sep 15, 2026Lets an AI client compose deterministic SVG diagrams, charts, and tables with embedded machine-readable metadata.
Also known as InnerAura/hyperweave
- Stars
- 61
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Sep 15, 2026
- License
- Apache-2.0
What is HyperWeave MCP?
HyperWeave lets an AI client compose deterministic SVG diagrams, charts, and tables with embedded machine-readable metadata.
Summary generated from the project's README
About HyperWeave MCP server
Generating deterministic visual artifacts like diagrams, charts, and tables from structured specifications is what hyperweave enables for AI agents and developers. By converting machine-readable JSON into self-contained SVG files, it provides a way for agents to communicate complex information visually without relying on fragile HTML or heavy raster images. These SVGs include embedded metadata, allowing an agent to read back the exact structure it originally drew.
Users can interact with the system through a CLI, an HTTP API, or an MCP server. The tool is designed with a zero-dependency philosophy, meaning it requires no JavaScript or runtime to render, making the resulting files compatible with any environment that supports standard image tags. It supports various diagram topologies including pipelines, state machines, trees, and directed acyclic graphs (DAGs). Because the artifacts carry their own specification and hash-verified digests, they can be used for durable memory, semantic diffing, or auditing mutation lineage across different steps in an agentic workflow.
What you can do with it
- 1Visualize complex system topologiesAn agent can generate a visual representation of a model router or a service pipeline using specific diagram types.
- 2Maintain durable agent memoryDevelopers can use generated artifacts as a way to store state that persists outside of the immediate context window.
- 3Perform semantic visual comparisonsYou can compare two different visual outputs based on their underlying data rather than comparing pixels.
- 4Enable agentic read-back capabilitiesAn AI client can extract the original structured data from an SVG to understand the diagram it previously created.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableinneraura/hyperweave is public and reachablegithub.com/inneraura/hyperweave ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-09-15github.com/inneraura/hyperweave ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubWhat Is HyperWeave
HyperWeave is a visual CLI for agents. Structured spec in, deterministic SVG out. Artifact classes include diagrams, charts, tables, and more. Each SVG is self-contained, with layout, theme, and machine-readable metadata compiled into the file.
Why It Exists
Humans can't keep pace with the volume of text agents produce. Pictures are the obvious fix, and every picture format gives something up. Markdown is portable but flat. HTML is expressive but fragile. Raster images travel well but discard their structure. Model output is flexible but never twice the same.
A HyperWeave artifact carries its own spec, so the thing your agent drew is the thing your agent can read back. Useful as:
- Chained steps: one agent's output is the next one's typed input.
- Memory: a committed artifact is durable state that survives the context window.
- Diffs: compare two artifacts semantically, not pixel by pixel.
- Audit: the spec, its provenance, and its mutation lineage travel with the image.
The picture is the record.
Philosophy
- Zero JavaScript.
- No runtime.
- No dependencies.
- One file, one request.
- Renders anywhere an
<img>tag does.
Artifact Format Comparison
| FORMAT | Portability | Agent-Readable Metadata | Visual Fidelity | Token Efficiency | Zero Dependencies | SCORE |
|---|---|---|---|---|---|---|
| SVG | ✓ | ✓ | ✓ | ~ | ✓ | 4.5 |
| Markdown | ~ | ~ | ✗ | ✓ | ✓ | 3.0 |
| HTML | ✗ | ✓ | ✓ | ✗ | ~ | 2.5 |
✓ full · ~ partial · ✗ none
Artifact Classes
Diagrams
Diagrams encode topology, not pixels. HyperWeave supports the following diagram types: pipeline, fanout, fanin, hub, cycle, loop, dag, lanes, state-machine, sequence, tree, and comparison. Nodes carry brand logo glyphs, labels, and tags. Edges carry labels and motion to help process information better. Every diagram renders as a self-contained SVG with its full spec and hash-verified digest embedded for agents to read directly. Render them in a markdown file, send to Slack as an image, or render directly in your terminal.
hyperweave compose diagram --spec-file /dev/stdin -g primer --variant porcelain --surface inlay --face light -o provider-router-light.svg <<'JSON'
{
"topology": "fanout",
"orientation": "horizontal",
"title": "One call, best model",
"subtitle": "Fanout · horizontal",
"zones": ["router", "providers"],
"node_style": "card+glyph",
"glyph_tint": "full",
"nodes": [
{ "id": "router", "label": "model router", "desc": "1 call, best model\ncapability-routed", "role": "hero", "kind": "router", "gather": true },
{ "id": "claude", "label": "Claude", "desc": "long-context", "glyph": "anthropic" },
{ "id": "gemini", "label": "Gemini", "desc": "multimodal", "glyph": "gemini" },
{ "id": "openai", "label": "OpenAI", "desc": "tool-use", "glyph": "openai" },
{ "id": "deepseek", "label": "DeepSeek", "desc": "reasoning", "glyph": "deepseek" },
{ "id": "kimi", "label": "Kimi", "desc": "agentic", "glyph": "kimi" },
{ "id": "qwen", "label": "Qwen", "desc": "multilingual", "glyph": "qwen" }
],
"edges": [
{ "source": "router", "target": "claude", "label": "route", "label_style": "chip", "relation": "drift", "marker": "arrow" },
{ "source": "router", "target": "gemini", "relation": "drift", "marker": "arrow" },
{ "source": "router", "target": "openai", "relation": "drift", "marker": "arrow" },
{ "source": "router", "target": "deepseek", "relation": "drift", "marker": "arrow" },
{ "source": "router", "target": "kimi", "relation": "drift", "marker": "arrow" },
{ "source": "router", "target": "qwen", "relation": "drift", "marker": "arrow" }
]
}
JSON
hyperweave extract broadcast-split-light.svg --respond payload > broadcast-split.json
hyperweave compose diagram --spec-file broadcast-split.json -g primer --variant porcelain --surface inlay --face light -o broadcast-split-light.svg
hyperweave extract compose-gate-light.svg --respond payload > compose-gate.json
hyperweave compose diagram --spec-file compose-gate.json -g primer --variant porcelain --surface inlay --face light -o compose-gate-light.svg
hyperweave compose diagram --spec-file pipeline-row -g primer --variant space --surface inlay --face light -o mcp-gateway-light.svg
pipeline-row is a bundled preset; the URL API renders it by name at /v1/diagram/pipeline-row/primer.static.
hyperweave extract verbs-mouth-light.svg --respond payload > verbs-mouth.json
hyperweave compose diagram --spec-file verbs-mouth.json -g primer --variant porcelain --surface inlay --face light -o verbs-mouth-light.svg
hyperweave compose diagram --spec-file dag-providers -g primer --variant noir --surface inlay --face light -o frontier-serving-light.svg
dag-providers is a bundled preset; the URL API renders it by name at /v1/diagram/dag-providers/primer.static.
hyperweave compose diagram --spec-file cycle-flow -g primer --variant porcelain --surface inlay --face light -o cycle-flow-light.svg
cycle-flow is a bundled preset; the URL API renders it by name at /v1/diagram/cycle-flow/primer.static.
hyperweave compose diagram --spec-file loop-hillclimb-turn -g primer --variant porcelain --surface inlay --face light -o loop-hillclimb-turn-light.svg
loop-hillclimb-turn is a bundled preset; the URL API renders it by name at /v1/diagram/loop-hillclimb-turn/primer.static.
hyperweave compose diagram --spec-file tree-health -g primer --variant porcelain --surface inlay --face light -o tree-health-light.svg
tree-health is a bundled preset; the URL API renders it by name at /v1/diagram/tree-health/primer.static.
Pick a layout
| Flows | pipeline · fanout · fanin |
stages in a line, one-to-many, many-to-one |
| Cycles | cycle · loop · state-machine |
a closed ring, a procedural loop with exits, legal state transitions |
| Structure | dag · tree · lanes |
dependencies, hierarchy, ownership rows |
| Centered | hub |
one thing at the middle of its world |
| Time | sequence |
who calls whom, in order |
| Side by side | comparison |
two options on one sheet |
Twelve layouts, fifty-nine bundled presets, one spec vocabulary. Variations are values of orientation, not layouts of their own:
dag · pipeline |
horizontal · vertical |
fanout |
horizontal · bilateral · upward · downward · radial |
tree |
horizontal · radial |
cycle |
ring · orbit |
loop |
vertical · horizontal |
fanin · hub · lanes · sequence · state-machine · comparison |
horizontal |
Render any preset by name at /v1/diagram/{preset}/primer.static, or run hyperweave discover diagram for every preset, orientation and field.
Matrices
HyperWeave matrices are structured tables rendered as portable SVGs. A single JSON description can produce comparison grids, registries, tiers, benchmark tables, heatmaps, chips, glyphs, bars, and status maps, while carrying a machine-readable payload for agents.
| READER | PIXELS | MOTION | READS VIA | |
|---|---|---|---|---|
| GitHub README | github | ✓ | Yes | camo, css animation |
| VS Code preview | vscode | ✓ | Yes | markdown preview |
| Slack unfurl | slack | ~ | - | image proxy |
| Gmail body | gmail | ~ | - | img tag |
| Agent | mcp | ✗ | - | hw:payload, hwz/1, markdown twin |
hyperweave compose matrix --spec-file /dev/stdin -g primer --variant porcelain -o one-artifact.svg <<'JSON'
{
"title": "One artifact. Many readers.",
"subtitle": "how each consumer ingests the same SVG",
"columns": [
{
"id": "reader",
"label": "READER",
"role": "label"
},
{
"id": "mark",
"label": "",
"kind": "glyph",
"glyph_tint": "full"
},
{
"id": "pixels",
"label": "PIXELS",
"kind": "check"
},
{
"id": "motion",
"label": "MOTION",
"kind": "pill"
},
{
"id": "via",
"label": "READS VIA",
"kind": "chip"
}
],
"rows": [
{
"label": "GitHub README",
"cells": [
{
"glyph": "github"
},
{
"state": "full"
},
{
"state": "on"
},
{
"chips": [
"camo",
"css animation"
]
}
]
},
{
"label": "VS Code preview",
"cells": [
{
"glyph": "vscode"
},
{
"state": "full"
},
{
"state": "on"
},
{
"chips": [
"markdown preview"
]
}
]
},
{
"label": "Slack unfurl",
"cells": [
{
"glyph": "slack"
},
{
"state": "partial"
},
{
"state": "off"
},
{
"chips": [
"image proxy"
]
}
]
},
{
"label": "Gmail body",
"cells": [
{
"glyph": "gmail"
},
{
"state": "partial"
},
{
"state": "off"
},
{
"chips": [
"img tag"
]
}
]
},
{
"label": "Agent",
"cells": [
{
"glyph": "mcp"
},
{
"state": "none"
},
{
"state": "off"
},
{
"chips": [
"hw:payload",
"hwz/1",
"markdown twin"
]
}
]
}
],
"notes": "pixels for humans · hw:payload for agents"
}
JSON
# Connectors preset
https://hyperweave.app/v1/matrix/connectors/primer.static?variant=porcelain
# Any table, one URL: base64url MatrixSpec JSON (8 KB cap)
https://hyperweave.app/v1/matrix/custom/primer.static?spec=<base64url>
HyperWeave MCP questions
What does HyperWeave generate?
It produces deterministic SVG diagrams, charts, and tables from a structured spec, with layout, theme, and metadata compiled into each file.
Does HyperWeave require JavaScript?
No. Artifacts are plain SVG with zero JavaScript, no runtime, and no dependencies, so they render anywhere an img tag works.
What diagram topologies does HyperWeave support?
It supports pipeline, fanout, fanin, hub, cycle, loop, dag, lanes, state-machine, sequence, tree, and comparison topologies.
Can an agent read data back out of a HyperWeave artifact?
Yes. Each SVG embeds its full spec and a hash-verified digest, which can be extracted back as structured payload.
How does an AI client use HyperWeave?
It can call the compose engine through the MCP server, the HTTP API, or the CLI.