Hound MCP server
Commit Nov 10, 2026Enables AI agents to perform browser automation using token-budgeted delta snapshots and self-healing selectors to minimize token consumption.
Also known as sumitrao9/hound
- Stars
- 0
- Tools
- 13
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 10, 2026
- License
- MIT
What is Hound MCP?
Hound enables AI agents to perform browser automation using token-budgeted delta snapshots and self-healing selectors to minimize token consumption. It exposes 13 tools, such as browser_open, browser_snapshot, browser_act.
Summary generated from the project's README
About Hound MCP server
Automating web browsers while minimizing token costs is what Hound enables for AI agents. It provides a specialized interface for navigating websites, interacting with elements, and extracting data through a set of thirteen tools including browser_act, browser_extract, and browser_find. Developers can run this server locally via stdio or deploy it as a hosted HTTP endpoint using API key authentication.
The system distinguishes itself by using delta snapshots that only return changed information and a budgeting mechanism that prevents massive token consumption. If a screenshot or PDF would exceed the specified max_tokens, the server returns size metadata instead of the full payload. It also features self-healing capabilities where the browser_heal tool can repair and remember CSS selectors for specific logical keys to ensure long-term automation stability.
Users can manage their resource usage through the browser_budget_report tool to monitor session spending. The server requires Playwright and Chromium to function and can be configured with environment variables like HOUND_DEFAULT_BUDGET to control how much information is passed to the AI client during each interaction.
What you can do with it
- 1Reduce web automation token costsAn AI agent can navigate complex websites while only receiving the specific changes between page states to save on context window usage.
- 2Maintain stable web scrapersWhen a website changes its layout, the agent can repair broken selectors and save the fix for future sessions.
Written from the project's README. Every use case is checked against a quote from it.
Hound MCP tools 13
Detected from the READMEbrowser_openbrowser_snapshotbrowser_actbrowser_findbrowser_extractbrowser_healbrowser_contentbrowser_evalbrowser_waitbrowser_scrollbrowser_screenshotbrowser_pdf
Show all 13 toolsShow fewer tools
browser_budget_report
Configuration
HOUND_API_KEYHOUND_DEFAULT_BUDGETHOUND_HEADLESSHOUND_HOSTHOUND_PORT
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 reachablesumitrao9/hound is public and reachablegithub.com/sumitrao9/hound ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-10github.com/sumitrao9/hound ↗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 model13 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubHound
Token-budgeted, self-healing browser automation MCP server for AI agents. Self-host (stdio) or run as a hosted HTTP/Streamable MCP endpoint with API-key auth.
What it is
Hound gives AI agents browser control with budgeted responses and delta snapshots (returns only what changed). It also heals selectors and remembers verified repairs per site.
Superpowers (13 tools)
| Tool | Purpose |
|---|---|
browser_open |
Navigate and get a budgeted snapshot (url) |
browser_snapshot |
Re-read page; delta by default (full_snapshot) |
browser_act |
action + target (ref like e3 or CSS), optional value — supports click/fill/press/select/hover |
browser_find |
Find by accessible text (optional role,limit) |
browser_extract |
Extract with root + fields map; confidence/verified |
browser_heal |
Repair selector for logical_key; verify & remember |
browser_content |
Budgeted, cleaned text extraction (page or selector) |
browser_eval |
Run JS in page context, return budgeted result |
browser_wait |
Wait for selector/text/state before next action |
browser_scroll |
Scroll page or element (up/down) |
browser_screenshot |
JPEG screenshot (base64 when within budget, else size metadata) |
browser_pdf |
PDF export (base64 when within budget) — Chromium |
browser_budget_report |
Session token spend + optimizer/selector stats |
All tools accept max_tokens and enforce budgeted responses (profile degradation + truncation reporting). Screenshots/PDFs are budget-aware: if the payload would blow the token budget, Hound returns size metadata instead of dumping base64.
Measured results
Benchmark (bench/run_fixed2.py, see bench/results/latest.json): baseline = full ARIA snapshot + body text per step; Hound = budgeted/delta.
| Page | Conventional | Hound | Reduction |
|---|---|---|---|
| example.com | 8,781 | 614 | 93.0% |
| news.ycombinator.com | 1,687 | 192 | 88.6% |
| en.wikipedia.org/wiki/Web_scraping | 212,358 | 1,145 | 99.5% |
Overall: 222,826 → 1,951 tokens (~99.1%). First snapshot has no delta baseline; results vary by page/flow.
Tools (7)
| Tool | Purpose |
|---|---|
browser_open |
Navigate and get a budgeted snapshot (url) |
browser_snapshot |
Re-read page; delta by default (full_snapshot) |
browser_act |
action + target (ref like e3 or CSS), optional value |
browser_find |
Find by accessible text (optional role,limit) |
browser_extract |
Extract with root + fields map; confidence/verified |
browser_heal |
Repair selector for logical_key; verify & remember |
browser_budget_report |
Session token spend |
Quick Start (self-host, stdio)
pip install git+https://github.com/sumitrao9/hound
playwright install chromium
hound-mcp
MCP client config:
{"mcpServers":{"hound":{"command":"hound-mcp","env":{"HOUND_DEFAULT_BUDGET":"1200","HOUND_HEADLESS":"1"}}}}
Run as 24/7 Hosted MCP (HTTP/Streamable)
export HOUND_API_KEY="your-secret-key" # optional but recommended for hosted
export HOUND_HOST=0.0.0.0
export HOUND_PORT=8000
hound-mcp-http
# MCP endpoint: http://HOST:8000/mcp (also mounted at /)
# Health: /health
Auth: send Authorization: Bearer <HOUND_API_KEY>. Supports HOUND_API_KEYS (comma-separated). No key set = open (dev only).
Docker
docker build -t hound-mcp .
docker run -p 8000:8000 -e HOUND_API_KEY=secret hound-mcp hound-mcp-http
Environment variables
| Variable | Default | Notes |
|---|---|---|
HOUND_DEFAULT_BUDGET |
1200 |
Token budget |
HOUND_MAX_BUDGET |
20000 |
Max budget |
HOUND_HEADLESS |
1 |
Headless browser |
HOUND_DB |
hound-selectors.db |
Selector memory DB |
HOUND_API_KEY / HOUND_API_KEYS |
(unset) | Bearer auth for HTTP mode |
HOUND_HOST / HOUND_PORT |
0.0.0.0 / 8000 |
HTTP bind |
HOUND_JSON_RESPONSE |
0 |
JSON responses vs SSE |
HOUND_STATELESS |
0 |
Stateless sessions |
Monetization / Support (use Hound)
- Hosted 24/7 MCP endpoint (managed, API key, usage limits) — request access / waitlist (INR ₹799–₹3,999/mo or $9–$49/mo + usage, estimate/validate; pay via Razorpay/Stripe/checkout link on approval).
- Pro/support: integration help, custom tools, authorized automation workflows.
- Agensi skill: installable skill package for local MCP setup.
- GitHub Sponsors / inquiries: https://github.com/sumitrao9/hound/issues
Safety & limitations
Only automate sites/data you are authorized to access. Respect ToS/law. Budgeting may truncate (use browser_find/browser_extract). Requires Playwright/Chromium.
Development
pip install -e ".[dev]"
ruff check .
pytest -v -m "not live"
License
MIT
Hound MCP questions
What tools does Hound MCP provide?
It exposes 13 tools, including browser_open, browser_snapshot, browser_act, browser_find, browser_extract.
How does Hound reduce token usage?
It uses budgeted responses and delta snapshots, returning only what has changed on the page rather than full trees.
Can Hound fix broken web elements?
Yes, it features self-healing capabilities that repair selectors and remember verified repairs for specific sites.
What authentication methods are supported for the hosted version?
The hosted HTTP/Streamable endpoint supports API-key authentication via Bearer tokens.