How do I use fast-browser-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@fast-browser-mcp Open http://localhost:3000 and generate a QA report" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

fast-browser-mcp

by donleqt

Overview Schema Source Related Servers Score Discussions Admin

TypeScript

Local

fast-browser-mcp

fast-browser-mcp is a lightweight MCP server that adds persistent QA state on top of agent-browser.

It does not rebuild browser automation. Instead, it shells out to agent-browser commands and stores compact session state on disk so AI agents can reason over changes across multiple steps.

Features

session-scoped storage (sessionId) instead of environment-scoped state
persistent snapshots, diffs, errors, timeline, and QA report
simple line-based diff optimized for AI readability
file-based architecture only (no database, no workers, no polling)
MCP-first tool interface for Cursor and other MCP clients

Related MCP server: MCP-RealBrowser

Why this project exists

AI-driven QA workflows lose context quickly between actions. This server keeps state per browser session so agents can:

compare state before/after each action
inspect recent console/network failures
generate concise QA reports from deterministic stored artifacts

Requirements

Node.js >=24 (required by agent-browser)
npm

agent-browser does not need to be installed globally. This package will use a local/global agent-browser if available, and falls back to npx agent-browser@latest when needed.

Installation

Option A: Run from npm (after publish)

npx fast-browser-mcp

Option B: Install globally from GitHub (no npm registry publish required)

Direct npm i -g github:... can leave a broken symlink in global node_modules on some npm setups. Use the pack-then-install flow instead:

bash <(curl -fsSL https://raw.githubusercontent.com/donleqt/fast-browser-mcp/main/scripts/install-global.sh)

Or manually:

tmpdir=$(mktemp -d) && \
tarball=$(npm pack github:donleqt/fast-browser-mcp --pack-destination "$tmpdir" --silent) && \
npm i -g "$tmpdir/$tarball" && \
rm -rf "$tmpdir"

Then run:

fast-browser-mcp

Option C: Build from source

git clone https://github.com/donleqt/fast-browser-mcp.git
cd fast-browser-mcp
npm install
npm run build
node dist/index.js

Cursor MCP configuration

Add a stdio MCP server entry:

{
  "mcpServers": {
    "fast-browser-mcp": {
      "command": "npx",
      "args": ["fast-browser-mcp"]
    }
  }
}

If installed globally:

{
  "mcpServers": {
    "fast-browser-mcp": {
      "command": "fast-browser-mcp",
      "args": []
    }
  }
}

Session model

every browser flow is keyed by sessionId
default sessionId is slug-safe and derived from URL
duplicate derived session IDs are reused by default
custom sessionId is supported

Examples:

http://localhost:3000 -> localhost-3000
https://app.example.com/dashboard -> app-example-com-dashboard

Storage layout

All artifacts are written under:

.fast-browser/
  sessions/
    {sessionId}/
      latest.md
      previous.md
      diff.md
      errors.md
      timeline.jsonl
      meta.json
      screenshot.png
      report.md

MCP tools

fast_browser_open({ url, sessionId? })
fast_browser_snapshot({ sessionId })
fast_browser_diff({ sessionId })
fast_browser_errors({ sessionId })
fast_browser_act({ sessionId, action, ref?, value? })
fast_browser_state({ sessionId })
fast_browser_report({ sessionId })
fast_browser_sessions({})

Quick example workflow

fast_browser_open({ url: "http://localhost:3000" })
fast_browser_state({ sessionId: "localhost-3000" })
fast_browser_act({ sessionId: "localhost-3000", action: "click", ref: "@e1" })
fast_browser_report({ sessionId: "localhost-3000" })

Architecture

src/agentBrowser.ts: centralized CLI mapping and execution wrapper
src/storage.ts: file-based session persistence
src/tools.ts: MCP tool handlers and orchestration
src/diff.ts: readable line-based diff
src/report.ts: report generation

Scope and non-goals (MVP)

This project intentionally does not include:

environment concepts (local/staging/prod)
database or cloud sync
authentication or multi-user orchestration
web UI, React/Redux hooks, polling loops, background workers

Troubleshooting

ENOTDIR or git dep preparation failed during global GitHub install
- remove any broken global install: rm -f "$(npm root -g)/fast-browser-mcp"
- reinstall using Option B above (pack-then-install), not npm i -g github:... directly
agent-browser CLI not found...
- ensure npx can run in your environment
- optionally install agent-browser globally for faster startup (npm i -g agent-browser)
- verify Node.js version is >=24
session not found errors
- run fast_browser_open first to create/reuse a session

Available Tools

8 tools

fast_browser_actB

Run one browser action and automatically refresh snapshot, diff, and errors.

ParametersJSON Schema

Name	Required	Description	Default
`ref`	No
`value`	No
`action`	Yes
`sessionId`	Yes

TDQS

B3/5.0

Behavior3/5

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

With no annotations, the description carries the full burden. It discloses that the tool automatically refreshes snapshot, diff, and errors after the action, which is useful. However, it omits other behavioral traits such as destructiveness, authorization needs, or side effects on session state.

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?

The description is exceptionally concise with a single sentence that front-loads the core action and side effect. Every word adds value, with no redundancy.

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

Completeness2/5

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

Given the tool's complexity (4 parameters, no output schema, no annotations) and the presence of many sibling tools, the description is inadequate. It fails to explain parameter usage, return behavior, or error states, leaving the agent with insufficient information to invoke the tool correctly.

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?

Schema description coverage is 0%, so the description must explain parameters. It does not mention 'sessionId', 'ref', or 'value', which are critical for correct invocation. Only 'action' is implied by 'browser action', but the meaning of 'ref' and 'value' remains unclear.

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

Purpose4/5

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

The description clearly states it runs one browser action (implying click, fill, type, press from the schema) and automatically refreshes snapshot, diff, and errors, distinguishing it from sibling tools that handle those side effects separately. It lacks specificity on the exact action types but is still clear.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, when not to use it, or contrast with sibling tools like fast_browser_state or fast_browser_report.

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

fast_browser_diffC

Return the latest saved diff for a session.

ParametersJSON Schema

Name	Required	Description	Default
`sessionId`	Yes

TDQS

C2.3/5.0

Behavior2/5

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

With no annotations, the description carries full burden for behavioral disclosure. It implies a read operation by stating 'Return', but does not mention whether the operation is safe, idempotent, or has side effects. Critical behaviors such as what happens if no diff exists, authentication requirements, or rate limits are omitted.

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

Conciseness2/5

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

The description is concise in word count (one sentence) but is under-specified for an agent to use effectively. It sacrifices necessary details for brevity, making it too sparse. While it avoids fluff, it omits important information that should be included.

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

Completeness1/5

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

Given the tool has one required parameter, no output schema, and no annotations, the description should compensate but fails to do so. It does not explain what a diff is, the output format, error conditions, or behavior when no diff exists. This is insufficient for an agent to correctly invoke and interpret results.

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

Parameters1/5

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

Schema description coverage is 0%, and the description adds no meaning to the sessionId parameter beyond what the schema provides (string, minLength 1). It fails to explain how the sessionId is used, format expectations, or constraints. For a single-parameter tool, the description should at least clarify the parameter's role.

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

Purpose4/5

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

The description clearly states the verb 'Return', the resource 'latest saved diff', and the context 'for a session'. It effectively distinguishes from sibling tools like fast_browser_snapshot and fast_browser_state, as it specifically retrieves a diff. However, it could be more explicit about what a 'diff' entails, such as comparing two snapshots.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. There is no mention of prerequisites, when it is appropriate, or when other tools like fast_browser_snapshot or fast_browser_report might be preferred.

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

fast_browser_errorsC

Collect console and network failures and store error summary.

ParametersJSON Schema

Name	Required	Description	Default
`sessionId`	Yes

TDQS

C2.4/5.0

Behavior2/5

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

Annotations are absent, so description must carry behavioral disclosure. It only says 'collect and store' without revealing side effects (e.g., whether it appends or replaces, if it clears previous errors, or if it requires an active session). Leaves critical behavioral traits unaddressed.

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

Conciseness3/5

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

Description is very short, but lacks structure such as examples, usage notes, or multiple sentences. It is minimal but not optimally informative. Every sentence should earn its place; here, one sentence attempts too much.

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

Completeness2/5

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

Given no output schema and no annotations, the description should compensate by explaining what the stored error summary contains, how it can be retrieved, or the lifecycle of the summary. It does not, leaving significant gaps.

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

Parameters1/5

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

Schema coverage is 0% and description provides no details about the required sessionId parameter. The agent gets no guidance on what sessionId represents or how to obtain it.

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

Purpose4/5

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

Description states it collects console and network failures and stores an error summary. This clearly indicates the tool's function but does not distinguish it from sibling tools that also deal with browser state, leaving some ambiguity.

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

Usage Guidelines2/5

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

No mention of when to use this tool over siblings like fast_browser_state or fast_browser_snapshot. Lacks context on prerequisites or scenarios.

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

fast_browser_openB

Open a URL, initialize/reuse a browser session, and store first snapshot.

ParametersJSON Schema

Name	Required	Description	Default
`url`	Yes
`sessionId`	No

TDQS

B3/5.0

Behavior3/5

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

With no annotations, the description carries the burden. It discloses that a browser session is initialized or reused, and a snapshot is stored. However, it does not explain what 'initialize' means, what happens on invalid URLs or sessionIds, browser type, or snapshot content. Some behavioral aspects are hinted but not fully transparent.

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

Conciseness4/5

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

The description is a single sentence that is front-loaded and contains no fluff. It covers the key actions efficiently. However, it could be slightly more structured by separating the URL opening from session management, but overall it is appropriately concise.

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

Completeness3/5

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

The tool is relatively simple with only 2 parameters and no output schema. The description adequately explains the core function, but it lacks context about how the snapshot is used by sibling tools or what constitutes a 'session'. For a tool that initiates browser automation, it could provide more context about subsequent steps.

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?

Schema description coverage is 0%, so the description must add meaning. It mentions 'Open a URL' for the url parameter, which is clear but doesn't specify the URI format (covered by schema). For sessionId, it implies the parameter via 'initialize/reuse a browser session', but does not explicitly map sessionId to that behavior. The description provides minimal added value over the raw schema.

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

Purpose4/5

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

The description clearly states the action (open a URL), the resource (URL), and additional actions (initialize/reuse session, store snapshot). It distinguishes itself from sibling tools like fast_browser_act and fast_browser_snapshot by being the entry point. However, the phrase 'initialize/reuse' could be more explicit about session management.

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

Usage Guidelines2/5

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

There is no guidance on when to use this tool versus alternatives. It does not specify that this is the first tool to call before using other browser tools, nor does it explain when to use a sessionId (e.g., existing session vs. new). Sibling tools exist for actions, diffs, etc., so usage context is missing.

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

fast_browser_reportC

Generate and save a QA report markdown file for a session.

ParametersJSON Schema

Name	Required	Description	Default
`sessionId`	Yes

TDQS

C2.7/5.0

Behavior2/5

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

With no annotations provided, the description bears full responsibility for behavioral disclosure. It states the tool saves a file, implying a write operation, but does not mention side effects like overwriting, file location, or permissions required. This is insufficient for safe invocation.

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?

The description is a single sentence of 11 words, with no redundant information. It efficiently conveys the core purpose, which is appropriate for a tool with one parameter.

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

Completeness2/5

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

Given the tool's simplicity (one parameter, no output schema), the description is too sparse. It omits important context such as what the report contains, where it is saved, and whether it overwrites existing files. This gap is not filled by annotations.

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

Parameters1/5

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

Schema description coverage is 0% (the single parameter sessionId lacks any description in the schema). The tool description does not add meaning beyond naming the parameter; it does not clarify the format or constraints of sessionId.

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

Purpose4/5

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

The description clearly states the tool generates and saves a QA report markdown file for a session, using a specific verb and resource. However, it lacks detail about the report's contents, which would further differentiate it from sibling tools like fast_browser_diff or fast_browser_errors.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives (e.g., for creating a structured summary vs. examining specific errors). There is no indication of prerequisites or context.

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

fast_browser_sessionsA

List all stored browser sessions.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A3.7/5.0

Behavior3/5

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

The description implies a non-destructive read operation, which is appropriate, but it fails to explicitly state safety or side effects. Since no annotations are provided, the description carries the full burden, but it lacks details on return format or data nature.

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?

The description is a single sentence of six words with no redundancy. Every word is essential for conveying the tool's action and target.

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

Completeness3/5

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

Without an output schema, the description should clarify what a 'session' entails or the format of the list. The current text is adequate for a simple tool but leaves ambiguity about the nature of the returned data.

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

Parameters4/5

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

There are zero parameters, so the description does not need to add parameter semantics. The baseline score of 4 applies as the schema coverage is 100% (void) and the description adds no conflict.

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 uses the verb 'List' and specifies the resource 'stored browser sessions', making the tool's purpose clear. It distinguishes itself from sibling tools like fast_browser_act or fast_browser_state by focusing solely on listing sessions.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives. The description does not mention prerequisites, context, or exclusions, leaving the agent to infer usage without explicit direction.

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

fast_browser_snapshotC

Capture a new snapshot and diff against previous snapshot.

ParametersJSON Schema

Name	Required	Description	Default
`sessionId`	Yes

TDQS

C2.7/5.0

Behavior2/5

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

No annotations are present, so the description carries full burden. It discloses that it captures and diffs, but does not mention side effects, whether it is destructive, or what happens to previous snapshots.

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

Conciseness4/5

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

The description is very concise at 8 words and front-loaded with the key action. However, it may be too brief to fully inform use.

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

Completeness2/5

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

Given the tool's simplicity (1 parameter, no output schema, no annotations), the description still lacks behavioral details, usage context, and parameter semantics, making it incomplete for effective agent selection.

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?

Schema description coverage is 0%, so the description must add meaning but does not. The single parameter 'sessionId' is not explained beyond its name and schema type; the purpose within the tool is inferred.

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

Purpose4/5

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

The description clearly states the tool captures a new snapshot and diffs against previous. The verb 'capture' and resource 'snapshot' are specific, and it distinguishes from the sibling tool 'fast_browser_diff' which likely only diffs existing snapshots.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives like fast_browser_diff. It does not specify prerequisites, context, or exclusions.

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

fast_browser_stateC

Return compact session QA state from files and recent timeline.

ParametersJSON Schema

Name	Required	Description	Default
`sessionId`	Yes

TDQS

C2.6/5.0

Behavior2/5

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

No annotations are provided, so the description carries full burden. It implies a read operation by 'Return' but does not disclose whether there are side effects, auth requirements, or rate limits. The mention of 'files and recent timeline' adds some context but is insufficient.

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

Conciseness4/5

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

One efficient sentence with no wasted words, appropriate for a simple tool. Could be slightly improved with structuring, but it is concise without being under-specified.

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

Completeness2/5

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

Given no output schema and no annotations, the description is too brief. It does not explain what 'QA state' contains, error conditions, or how the sessionId relates to the return value, leaving the agent with incomplete information.

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

Parameters1/5

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

Schema has 1 parameter (sessionId) with 0% description coverage, yet the description provides no additional meaning about the parameter, such as its format or purpose beyond what the schema minimally states.

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

Purpose4/5

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

The description clearly states the tool returns compact session QA state from files and recent timeline, with a specific verb and resource that distinguishes it from siblings like fast_browser_act or fast_browser_snapshot.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus alternatives. With siblings for actions, diffs, errors, etc., the description should indicate the appropriate context for invoking this state-retrieval tool.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

8 tool updatesv0.1.0Jul 5, 2026
- First observedfast_browser_act
- First observedfast_browser_diff
- First observedfast_browser_errors
- First observedfast_browser_open
- First observedfast_browser_report
- First observedfast_browser_sessions
- First observedfast_browser_snapshot
- First observedfast_browser_state

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.3/5.0

Scored 2026-07-05 15:00 across 8 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: act performs an action, diff returns diffs, errors collects logs, open starts a session, report generates a report, sessions lists sessions, snapshot captures snapshots, and state returns session state. No overlaps.

Naming Consistency5/5

All tools follow a consistent snake_case pattern with the 'fast_browser_' prefix and a verb_noun structure (e.g., fast_browser_act, fast_browser_diff). No deviations.

Tool Count5/5

8 tools is well-scoped for a browser automation server, covering core operations (open, act, snapshot, diff, errors, report, sessions, state) without being overly numerous or sparse.

Completeness4/5

The set covers key lifecycle operations (open, act, capture, diff, report), but missing an explicit 'close' or 'quit' tool for tearing down sessions, which may be a minor gap.

Maintenance

ActivityStale

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Before Users DoOAuth
io.github.bhuman-ai
Browser-backed QA with evidence and fix-ready reports for coding agents.
Browser Automation Testing & QA Tools Coding Agents
1
aiqaramba
io.github.ajrogier
Browser-based QA for AI-built software. Test pages with real browsers via agents.
Testing & QA Tools Browser Automation Agent Orchestration
2
Work Context ProtocolOAuth
io.workcontextprotocol
Persistent work tracking for AI agents: tasks, status and history that follow you across machines
Project Management Knowledge & Memory
1
TestMu AI (formerly LambdaTest)OAuth
io.github.LambdaTest
Agentic testing: HyperExecute jobs, test failure triage, SmartUI visual diffs, a11y audits
Testing & QA Tools CI/CD & DevOps Browser Automation
1

Related MCP Servers

LAM-mcp Browser Automation
Browser Automation Web Scraping
Gafoor2005
A
license
Not graded
quality
C
maintenance
Enables AI assistants to perform intelligent browser automation with session-based context analysis, including navigation, form filling, and content extraction through natural language.
Updated 5 months ago (2026-04-21 07:08 UTC)
MIT
MCP-RealBrowser
Browser Automation Web Scraping
obbbba
A
license
Not graded
quality
B
maintenance
Provides a persistent browser profile for AI agents, enabling them to log in once and maintain sessions across restarts. Supports 20 tools for browsing, navigation, text extraction, and screenshot.
Updated 2 months ago (2026-07-19 13:47 UTC)
1
MIT
AI Web Tester
Browser Automation Testing & QA Tools Developer Tools
SiamAlSobari
A
license
Not graded
quality
B
maintenance
Enables AI coding agents to autonomously interact with and test web applications in a real browser, providing DOM/Accessibility tree extraction, runtime telemetry, screenshot capture, and Markdown test reports.
Updated 10 days ago (2026-08-30 14:03 UTC)
359
1
MIT
QualityMax QA MCPofficial
Web Scraping Testing & QA Tools
Quality-Max
A
license
A
quality
A
maintenance
Enables coding agents to independently verify web changes by scanning pages, inspecting UI structure, generating Playwright reproductions, and executing tests with structured QA evidence.
Updated 2 days ago (2026-09-07 12:36 UTC)
4
148
2
MIT

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/donleqt/fast-browser-mcp'

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

fast-browser-mcp

Features

Why this project exists

Requirements

Installation

Option A: Run from npm (after publish)

Option B: Install globally from GitHub (no npm registry publish required)

Option C: Build from source

Cursor MCP configuration

Session model

Storage layout

MCP tools

Quick example workflow

Architecture

Scope and non-goals (MVP)

Troubleshooting

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

QualityMax QA MCPofficial

Latest Blog Posts

MCP directory API