Agiliton
Feature comparison

Five field leaders. Twenty capabilities.

SiteBridge vs Claude for Chrome, Playwright MCP, Browser MCP, and Chrome DevTools MCP. Every cell traces to a public-facing source or a file path in the SiteBridge repo. No hand-waving. ships it   partial   doesn’t.

CapabilitySiteBridgeClaudeforChromePlaywrightMCPBrowserMCPDevToolsMCP
Bundled with model + agent runtime (no third-party sub)
Runs inside your real logged-in browser1
Works with any LLM provider (no model lock-in)2
Local-only data path possible3
Pre-click safety guards (expectedTarget, viewport check)
Undo log + DOM snapshot ring buffer
Compound wait-aware tools (click+wait+read)4
Cross-session selector learning
Semantic search across open tabs
Markdown negotiation (~10× token reduction)
Userscript / JS injection / CSS overlay5
Network capture + custom HTTP requests
Performance tracing (Core Web Vitals)
GIF recording with click indicators
Element-selection human handoff
Domain integrations (Smartling/n8n/Confluence/GDocs/Jira)
Per-MCP-client session isolation (Tab Groups)N/A6
Clipboard-routed secrets (no transcript leak)
Customer-held audit + enterprise kill-switch (attestable)7
No category blocklist (finance / high-ROI domains allowed)8
Documented tool count30+~540+~829
  1. Chrome DevTools MCP can attach to your real Chrome but only after relaunching with --remote-debugging-port=9222 every session — characterized as “torture” in published comparisons.
  2. Claude for Chrome runs only against Anthropic’s own models, gated to paid plans (Pro = Haiku 4.5; Max/Team/Enterprise = Sonnet 4.5 / Opus 4.5).
  3. Claude for Chrome inference happens on Anthropic’s servers — fine for many uses, blocking for regulated workloads.
  4. Implicit browser-native waits, but no documented compound primitive that combines click + navigate + settle + read in one call.
  5. Anthropic’s blog explicitly lists capabilities as “clicking, form-filling, navigation” only.
  6. Playwright MCP spawns its own browser — per-client isolation is automatic but at the cost of throwing away cookies, MFA tokens, browser extensions, and your real fingerprint.
  7. Core edition (SBD-84): hash-chained audit log drains over OTLP to a collector the customer runs; Chrome enterprise policy can kill-switch or deny action classes from the buyer’s side. The vendor cannot override managed policy. None of the four competitors ship a customer-held, attestable control plane.
  8. Anthropic’s extension blocks financial-services and adult-content sites by default — publicly admitting they don’t trust the agent in the high-value domains where automation has the most ROI. SiteBridge has no category blocklist because the safety stack is structural (audit + undo + pre-click guards), not a list of forbidden URLs.
Three lines that close the room

The numbers and tells behind the matrix.

Pull these when the comparison table alone isn't enough. Each one is single-source and dated.

The Anthropic tell

Finance sites are on their default blocklist.

Claude for Chrome blocks financial-services and adult-content sites out of the box. That is Anthropic publicly admitting they do not trust the agent in the high-value domains where automation has the most ROI. SiteBridge has no category blocklist — the safety stack is structural (audit + undo + pre-click guards), not a list of forbidden URLs.

1 in 9 still succeeds

11.2% post-mitigation prompt-injection rate.

Anthropic's own blog: 23.6% before mitigations, 11.2% after. One in nine attacks still gets through on the official extension. SiteBridge's expectedTarget pre-click guard plus the undo snapshot ring is defense-in-depth for exactly the cases where the model is fooled.

SBD-84 · Core edition

They buy what they can attest.

Regulated buyers do not judge features — they judge controls they can prove. Core edition ships a hash-chained audit log that drains over OTLP to a collector the customer runs, plus a Chrome enterprise-policy kill-switch and mutation gate the vendor cannot override. A bank can prove the control fired in a customer-held, tamper-evident record. None of the four competitors ship this.

Pick the right AI for each job

One product. Every major model.

SiteBridge routes browser tasks to the model that fits — cheap ones to fast small models, hard reasoning to the big ones. Hover the chart to see how the routing decision lands per task type.

1. pick a task
2. LiteLLM routes it
prompt
LiteLLM
+ MCP context
MiniMax
low-cost router

Browser navigation: find-button-and-click. Doesn't need reasoning. Route to the cheapest fast model — that's most of agent traffic.

cost / 1M tok$0.30
latency p500.8s
3. force any model
The safety check, hands-on

Try the pre-click guard.

Type what the agent intends to do, then type (or pick) what the page actually shows. The guard accepts, refuses, or asks for help — same logic that gates every click in production.

The pre-click guard compares the agent's stated intent to the dialog actually shown. Hidden swaps, prompt-injected destructive verbs, and ambiguous confirms get caught here — before the click goes through.

simulated browser dialog
example.com says

Save changes to comment? Your draft will be preserved.

CancelOK
click allowed
intent and dialog share 3 key terms — consistent
term overlap
75%
matched terms
save, draft, comment