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 skills/context-dot-dev/cursor-plugin/connect-context-devnpx skills add context-dot-dev/cursor-plugin --skill connect-context-devgit clone --depth 1 https://github.com/context-dot-dev/cursor-pluginWhat 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 | $0.00048 | $0.00448 |
| Opus 5 | $0.00024 | $0.00224 |
| Sonnet 5 | $0.00010 | $0.00090 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
connect-context-dev 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 yesterday.
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.
What it actually says
Connect Context.dev in Cursor
Standard connection
- Open Cursor Settings → Tools & MCP.
- Find the
contextserver installed by this plugin and enable it. - Select Connect or Authenticate.
- Complete the Context.dev sign-in and consent flow in the browser.
- Return to Cursor and confirm that the server lists its tools.
The plugin uses the production Streamable HTTP endpoint at https://mcp.context.dev/mcp. OAuth is discovered from the server automatically. Do not add headers, client secrets, or API keys to mcp.json.
Verify
Use a read-only request:
Use Context.dev to scrape https://www.context.dev and return the page title.
The agent should call web-scrape-markdown. A successful tool call confirms both the MCP connection and the authenticated Context account.
Troubleshooting
| Symptom | Action |
|---|---|
context is missing |
Refresh or reinstall the plugin, then reload the Cursor window |
| A second legacy Context.dev server appears | Remove the old manual server and reinstall this plugin |
| 401 or authentication required | Disconnect the server, reconnect it, and complete OAuth again |
| Browser flow does not open | Open the server details and select Authenticate manually |
| Tools remain unavailable after OAuth | Reload the Cursor window and re-enable the server |
| Account has insufficient credits | Review usage in the Context.dev dashboard; do not repeatedly retry |
Never ask the user to paste an OAuth token or private API key into chat.
Direct API development
OAuth covers Cursor's MCP connection. A user only needs an API key when writing their own application against the Context.dev REST API or SDK. In that case, direct them to the Context.dev dashboard and store the key in a server-side CONTEXT_DEV_API_KEY environment variable. Do not place it in this plugin's MCP configuration.
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.
- yesterday First seen · 44 lines · 48 tokens per session scan A 4bce209ea959
connect-context-dev is a skill published in the GitHub repository context-dot-dev/cursor-plugin (4 stars, last pushed 14d ago), licensed MIT. It adds 48 tokens to every session and 448 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…