Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/duvinc/duvlify/mcpgit clone --depth 1 https://github.com/DuvInc/duvlifyWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00034 | $0.02037 |
| Opus 5 | $0.00017 | $0.01019 |
| Sonnet 5 | $0.00007 | $0.00407 |
| Haiku 4.5 | $0.00003 | $0.00204 |
Grade A, and why
mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The manifest, WebMCP and limits
The manifest
src/lib/agent-manifest.ts emits
dist/agent-manifest.json at build time. For each page it records the
page's identity and length. For each heading it records the full path (for
example, "Custom domains › DNS records"), the anchor, and the start and
end lines.
One rule makes the whole thing work: line numbers are counted against the
exact bytes the site serves. The same pageMarkdown() output is what
<page>.md returns, what fetch returns, and what the indexer uploads. If
these ever diverge, every line range silently starts pointing at the wrong
paragraph.
This is also how a passage gets a heading. AI Search returns chunk text but not its position. So the Worker finds the text back inside the page and maps the resulting line to the heading whose range contains it. It does this at chunk granularity, which no per-page metadata field could ever express.
WebMCP
There are two ways to register these tools with an in-browser agent, and duvlify.dev runs the first.
Set agents.webmcpBridge to 'on' and this repository registers them
itself, from
src/components/WebMcpBridge.astro.
This is the default here, and it is the only option for a deployment
under a subpath or on a domain that is not a Cloudflare zone.
The alternative is Cloudflare's hosted bridge, which costs nothing to maintain. In the dashboard, go to Agent Readiness → Labs → Enable WebMCP, then under Tool packs check Site MCP server only.
The interface says "Leave every pack unchecked to use the default set". The default set is actually all packs, including a C2PA image-provenance scanner. That scanner is pure noise on a documentation site, and it costs context in every agent that loads the page. Check the one pack explicitly instead.
That pack proxies this site's own /mcp. Cloudflare does not supply a
generic documentation MCP. It finds this site's server at <origin>/mcp,
which is why the MCP endpoint lives on the site's Worker rather than on one
of Cloudflare's own.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 173 lines · 34 tokens per session scan A 8e9b80a77431
mcp is an agent published in the GitHub repository DuvInc/duvlify (23 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 2,037 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
mcp-connection
Connect Claude Code or any MCP-compatible agent to your Projektor instance.
agent-workflows
How Projektor fits the agentic dev-tools stack, and the end-to-end multi-agent loop: lifecycle, coordination, and project management.
research-experimental
Research experimental TouchDesigner techniques including GLSL, GPU compute, ML integration.
enhance-core-tools
Enhance core search, operators, and workflow tools with new capabilities.
implement-experimental
Implement MCP tools for experimental techniques and add experimental operator data.
research-td-versions
Research all TouchDesigner versions and create version compatibility data.