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/tajd/projektor/mcp-connectiongit clone --depth 1 https://github.com/TAJD/projektorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/tajd/projektor/mcp-connection)<a href="https://agentmods.dev/agents/tajd/projektor/mcp-connection"><img src="https://agentmods.dev/badge/agents/tajd/projektor/mcp-connection.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00014 | $0.04079 |
| Opus 5 | $0.00007 | $0.02039 |
| Sonnet 5 | $0.00003 | $0.00816 |
| Haiku 4.5 | $0.00001 | $0.00408 |
Grade A, and why
mcp-connection scanned grade A with 1 finding 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 today.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://<your-worker>.workers.dev/bootstrap" \ How it starts
The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connect Claude Code (or any MCP-compatible agent) to your projektor instance.
1. Prerequisites
- A running projektor instance. See the self-hosting guide or the full deploy guide.
- Claude Code installed.
npm install -g @anthropic-ai/claude-code(or the desktop/IDE app). - A projektor API token. Two ways to get one:
- Development — use the bootstrap endpoint (see §2 below). No login required; needs
BOOTSTRAP_SECRET. - Production — log in through the UI → Settings → Tokens → "New token"; or mint one via the REST API (see §3).
- Development — use the bootstrap endpoint (see §2 below). No login required; needs
Using the Claude Code CLI? Continue to §2/§3 below. Using the Claude app (desktop or web) instead? Skip to §3b. Connect the Claude app.
2. One-shot connect (dev / bootstrap)
The bootstrap endpoint provisions a workspace, user, and token in a single call, then prints the exact claude mcp add command to run. Use this for local dev or staging environments where BOOTSTRAP_SECRET is set.
# 1. Bootstrap workspace + token
curl -s "https://<your-worker>.workers.dev/bootstrap" \
-H "X-Bootstrap-Secret: <your-secret>"
# Response includes mcpAddCommand - pipe it straight to your shell:
curl -s "https://<your-worker>.workers.dev/bootstrap" \
-H "X-Bootstrap-Secret: <your-secret>" \
| jq -r .mcpAddCommand | sh
Local dev (BOOTSTRAP_SECRET defaults to localdev in .dev.vars.example):
curl -s http://127.0.0.1:8787/bootstrap \
-H "X-Bootstrap-Secret: localdev" \
| jq -r .mcpAddCommand | sh
The bootstrap endpoint is enabled only when ENVIRONMENT=development — any other value, including an unset one, disables it. It is idempotent, so it's safe to call more than once.
3. Manual connect (production)
Mint a token from the UI (Settings → Tokens) or via the API, then add the MCP server:
claude mcp add \
--transport http \
--header "Authorization: Bearer pk_<64 hex chars>" \
--header "X-Workspace-Slug: <slug>" \
projektor "https://<your-worker>.workers.dev/mcp/<workspace-uuid>"
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.
- today Changed · +5 lines 760ebe864119
- 4d ago First seen · 337 lines · 14 tokens per session scan A c4231b4f9c80
mcp-connection is an agent published in the GitHub repository TAJD/projektor (39 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 4,079 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
retrieval
Two retrieval backends: a lexical index built at compile time that needs no account, and Cloudflare AI Search for hybrid semantic search when you want it.
discovery
How an agent finds these surfaces without being told: the API catalog, DNS-based discovery, an agent-skills index, and the places people actually look.
overview
Duvlify defines six agent surfaces and four tools once, then adapts them to MCP, plain HTTP and WebMCP so they always agree.
mcp
The page outline agents read for line offsets, the in-browser WebMCP bridge and when to run it yourself, the rate limits, and how the surfaces are tested.
builder
Implements a single PLAN.md task in TypeScript (Next.js or Bun). Builds and self-tests; never commits unless told. Dispatched by /build-loop.
reviewer
Read-only code + security gate for a single built task (TypeScript, Next.js or Bun). Returns PASS or FAIL with findings. Dispatched by /build-loop.