pbi-webview2 (bibiibjorn/pbi-webview2) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 55 tools. No publisher has claimed this listing.
Enables AI agents to interact with live Power BI Desktop report canvas via Chrome DevTools Protocol, performing actions like page navigation, clicking slicers, reading cards and matrices, and capturing baselines.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
bibiibjorn
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
PBI_CDP_ENDPOINT"env": { "": "http://127.0.0.1:9222" }PBI_DESKTOP_BRIDGEExplicit path to Microsoft's powerbi-desktop bridge CLI entry (.js run under Node, or a .cmd/.bat/.exe). Tried first by pbi_launch.PBI_DESKTOP_EXEExplicit path to PBIDesktop.exe for the direct-launch fallback (used when no bridge CLI is found).PBI_EVAL_BUDGET_MS30000 Per-page.evaluate time budget; a read that lands mid-render fails fast with a renderer-busy error instead of hanging.PBI_OUTPUT_DIRos tmpdir>/pbi-webview2-output Where screenshots + baselines are written (never the repo/CWD).PBI_POLL_MS1000 Steady interval between poll probes inside the multi-step tools. Polls ramp adaptively from ~250ms toward this value, so warm/ready pages satisfy fast.PBI_SETTLE_MS700 Post-navigation settle in pbi_goto_page (waitReady) for late-binding visuals; only paid when the canvas isn't already stable. 0 disables it.ProgramFilesfrom PBI_DESKTOP_EXE, then %%\Microsoft Power BI Desktop\bin\PBIDesktop.exe,Dependencies
3 dependencies, 1 flagged: playwright-core
Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
55/55 tools missing one or more hints — pbi_launch (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); pbi_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); pbi_pages (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +52 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Descriptions match behaviour
2 tools describe read intent but their handlers mutate — pbi_baseline (line 51: fs.mkdirSync(dir, { recursive: true })); pbi_diff_state (line 51: fs.mkdirSync(dir, { recursive: true }))
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
44/55 tool handlers declare input schemas (80%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tests exist
No test files found
Add tests that exercise each declared tool.
No eval / new Function
3 eval() or new Function() calls — dynamic code execution
Replace eval / Function with explicit parsing or safer alternatives.
Shell command execution
7 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Tool description accuracy
pbi_baseline: description implies read-only but handler writes/deletes/executes; pbi_diff_state: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/bibiibjorn/pbi-webview2)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check