WaveXisMCP

wavexis_session_open

Launch a persistent browser session and return a reusable session ID for multi-step automation. Initialize once at task start to maintain browser state across subsequent calls.

Instructions

Launch a persistent browser session for multi-step workflows.

Call once at the start of a task and reuse the returned session_id for all subsequent calls; use wavexis_navigate with session_id omitted for one-off page fetches instead.

Side effects: Launches a browser process (or connects to an existing one) and allocates server-side session state; may open network connections to remote/cloud browsers. Returns: JSON string with keys: 'status' ('ok'/'error'), 'session_id' (str), 'backend' (str).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`input`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed14 schema fields changedv1.6.24Jul 29, 2026

addedInput schema / $defs / SessionOpenInput / properties / backend / enum
```
Added value: +[
+  "cdp",
+  "bidi",
+  "auto"
+]
```

addedInput schema / $defs / SessionOpenInput / properties / browser

Added value: +{
+  "default": "chrome",
+  "description": "Browser engine for BiDi backend: 'chrome' (chromedriver) or 'firefox' (geckodriver). Only used when backend='bidi'.",
+  "enum": [
+    "chrome",
+    "firefox"
+  ],
+  "title": "Browser",
+  "type": "string"
+}

addedInput schema / $defs / SessionOpenInput / properties / browser_url

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "WebSocket URL of an existing browser (e.g. ws://localhost:9222)",
+  "title": "Browser Url"
+}

addedInput schema / $defs / SessionOpenInput / properties / connect_existing

Added value: +{
+  "default": false,
+  "description": "Launch Chrome with --remote-debugging-port and connect to it. Useful for reusing an existing browser profile with logged-in sessions. The browser is launched headed (headless is ignored).",
+  "title": "Connect Existing",
+  "type": "boolean"
+}

addedInput schema / $defs / SessionOpenInput / properties / extra_headers / description
```
Added value: +"Extra HTTP headers to send"
```
addedInput schema / $defs / SessionOpenInput / properties / headless / description
```
Added value: +"Run browser in headless mode"
```
addedInput schema / $defs / SessionOpenInput / properties / height / description
```
Added value: +"Viewport height in pixels"
```
addedInput schema / $defs / SessionOpenInput / properties / proxy / description
```
Added value: +"Proxy server URL (e.g. http://host:port)"
```

addedInput schema / $defs / SessionOpenInput / properties / remote_url

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Cloud browser WebSocket URL",
+  "title": "Remote Url"
+}

addedInput schema / $defs / SessionOpenInput / properties / stealth

Added value: +{
+  "default": false,
+  "description": "Enable anti-bot stealth mode",
+  "title": "Stealth",
+  "type": "boolean"
+}

addedInput schema / $defs / SessionOpenInput / properties / timeout / description
```
Added value: +"Operation timeout in ms"
```
addedInput schema / $defs / SessionOpenInput / properties / user_agent / description
```
Added value: +"Custom User-Agent string"
```

addedInput schema / $defs / SessionOpenInput / properties / user_data_dir

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Persistent Chrome user data directory",
+  "title": "User Data Dir"
+}

addedInput schema / $defs / SessionOpenInput / properties / width / description
```
Added value: +"Viewport width in pixels"
```

First observedv1.0.1Jul 7, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses side effects: launches browser process, allocates server-side state, may open network connections. This adds value beyond annotations (openWorldHint, destructiveHint) and matches them. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is concise with one sentence each for purpose, usage, side effects, and return. Every sentence is informative and front-loaded with the main purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (14 parameters, many siblings, annotations, no output schema but described), the description covers purpose, usage, side effects, and return format adequately. The parameter details are in the schema, so completeness is high.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool description does not describe any of the 14 parameters; schema descriptions are present but the context signal shows 0% schema_description_coverage in the description. With low coverage, the description should compensate, but it does not. Only a basic mention of the return structure is provided.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool launches a persistent browser session, using the verb 'Launch' and the resource 'browser session'. It distinguishes from sibling `wavexis_navigate` by specifying that `wavexis_navigate` with session_id omitted is for one-off fetches.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly instructs to call once at task start and reuse the session_id, and contrasts with `wavexis_navigate` for one-off page fetches. Provides clear when-to-use and when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/MathiasPaulenko/wavexis-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server