spector-agent-mcp (sakitam-fdd/spector-mcp) is an MCP server listed on the M8ven Trust Index. It scores 59 out of 100, grade D. It declares 40 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
D
Caution
59/100

spector-agent-mcp

AI-first WebGL 1/2 debugging MCP server that attaches to Chrome via CDP, enables frame capture and diagnostic analysis, and collaborates with Chrome DevTools MCP for agent-driven debugging workflows.

→ sakitam-fdd/spector-mcp· listed on glama

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

⚡ Live Monitored: not connected

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

sakitam-fdd

Source: Glama

Is this your MCP?

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 →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here

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.

// key findings
⚠️
Tool descriptions don’t match what handlers do
1 tool describes read intent but its handler mutates — webgl_open_capture_viewer (line 131: writeFile(generatedViewerPath, html, "utf8"))
🚨
Known vulnerabilities in dependencies: 1 critical, 1 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
🔐
You'll be asked for 1 credential: SPECTOR_AGENT_MCP_HTTP_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes40 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

webgl_list_canvases

Enumerate WebGL/WebGL2 canvases on the bound page.

webgl_select_canvas

Select the WebGL canvas to capture.

webgl_capture_frame

Capture the next WebGL frame. Auto-connects, binds readiness checks, installs runtime if needed. Returns summary + resource URIs (not full JSON).

webgl_capture_sequence

Capture a limited sequence of frames (max 5).

webgl_list_captures

List stored captures, optionally filtered by session.

webgl_get_capture_overview

Get a stored capture summary and resource URIs.

webgl_run_diagnostics

Run deterministic diagnostic rules on a capture (no LLM). Returns findings summary.

webgl_get_finding_details

Get full evidence and hypotheses for a diagnostic finding.

webgl_diff_captures

Semantically compare two captures (findings, programs, draw counts).

webgl_generate_report

Generate Markdown and/or JSON diagnostic report for a capture.

webgl_list_draw_calls

Paginated list of draw/clear commands for a capture.

webgl_get_command_details

Get details for a single command with optional field includes.

webgl_list_programs

List shader programs in a capture.

webgl_get_program_details

Get shader sources and link/compile status for a program.

webgl_list_textures

List textures and upload metadata from a capture.

webgl_list_framebuffers

List framebuffers and attachments from a capture.

webgl_get_state_diff

Get initial vs final GL state differences for a capture.

webgl_search_capture

Search commands by API name, marker, object name, or stack frame text.

webgl_page_evaluate

Evaluate a JS expression in the bound page. Disabled by default; requires --allow-page-evaluate.

webgl_set_marker

Set a Spector.js marker string so subsequent captured commands are tagged (stage annotation at any point).

webgl_clear_marker

Clear the current Spector.js marker.

webgl_runtime_log

Write a custom log line into the Spector capture stream (appears as a log command when capturing).

webgl_screenshot_canvas

Immediate canvas.toDataURL screenshot (not a Spector frame). Useful for any-stage visual checks and goal verification. Saves under the current session screenshots/ folder.

webgl_read_console

Return recent console API messages collected from the bound page via CDP (log/warn/error).

webgl_list_visual_attachments

List Spector VisualState attachment screenshots persisted for a capture (requires capture with includeThumbnails=true, quickCapture=false).

webgl_get_visual_attachment

Resolve a single FBO/canvas screenshot path for AI inspection (Read tool can open the absolute file path).

webgl_capture_commands

Spector startCapture for a fixed command count — capture an arbitrary stage without waiting for a full frame boundary.

webgl_list_rules

List deterministic WebGL diagnostic rule IDs available to webgl_run_diagnostics.

webgl_debug_playbook

Given a URL/goal/symptoms, return a deterministic multi-phase tool sequence for AI automated WebGL debugging (attach → capture → diagnose → fix → verify).

webgl_session_create

Create a local debug session and connect to Chrome at the configured browser URL.

webgl_session_status

Get current session, target binding, and Spector runtime status.

webgl_list_targets

List Chrome page targets that can be bound for WebGL debugging.

webgl_bind_target

Bind a page target by targetId, debugSessionId, url+title, or urlPattern. Prefer debugSessionId set via chrome-devtools-mcp.

webgl_unbind_target

Detach from the currently bound page target.

webgl_runtime_install

Inject Spector.js into the bound page (early + late install).

webgl_runtime_status

Check Spector injection, canvas, and context status on the bound page.

webgl_export_capture

Export a capture tree (manifest, capture, findings, report) to a directory.

webgl_delete_capture

Delete a stored capture and its artifacts.

webgl_cleanup_store

Evict captures by TTL, per-session cap, and max store size.

webgl_open_capture_viewer

Return a local file URL for the read-only Capture Viewer pointing at a stored capture.

// known CVEs in dependencies1 critical1 high1 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@3.2.3GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

highws@8.18.2GHSA-96hv-2xvq-fx4p

ws: Memory exhaustion DoS from tiny fragments and data chunks

lowws@8.18.2GHSA-58qx-3vcg-4xpx

ws: Uninitialized memory disclosure

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configCHROME_PATH
configDEMO_URL
configSPECTOR_AGENT_MCP_HTTP_HOST
configSPECTOR_AGENT_MCP_HTTP_PATH
configSPECTOR_AGENT_MCP_HTTP_PORT
🔐 secretSPECTOR_AGENT_MCP_HTTP_TOKENexport ="replace-with-at-least-24-random-characters"
configSPECTOR_AGENT_MCP_TRANSPORT
configSPECTOR_BUNDLE_PATH
configWEBGL_DEBUG_BROWSER_URL
configWEBGL_DEBUG_LOG_LEVEL
configWEBGL_DEBUG_STORE_DIR
// quality suggestions

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

40/40 tools missing one or more hints — webgl_list_canvases (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); webgl_select_canvas (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); webgl_capture_frame (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +37 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

1 tool describes read intent but its handler mutates — webgl_open_capture_viewer (line 131: writeFile(generatedViewerPath, html, "utf8"))

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool inputs are validated

33/40 tool handlers declare input schemas (83%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool test coverage

Only 5/40 tools referenced in tests (13%)

Write tests that reference each tool by name so every tool has at least one test.

No eval / new Function

1 eval() or new Function() call — dynamic code execution

Replace eval / Function with explicit parsing or safer alternatives.

Shell command execution

9 child_process calls — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Production dependencies are patched

0 critical, 1 high severity in production deps — ws@8.18.2 (high), ws@8.18.2 (low)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dev dependencies

1 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Dependency freshness

1/5 production deps stale: spectorjs@2024-02-01 (2.5y)

Tool description accuracy

webgl_open_capture_viewer: 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.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 10 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/sakitam-fdd/spector-mcp?variant=verified)](https://m8ven.ai/mcp/sakitam-fdd/spector-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 978e300c858d7b5a4e789888e5e85fba7a690a11
code hash: 69be9df479cc49f01c169545d6a00cc4085d746527a6728167c4eede17597962
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

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
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client