Wraith MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| navigateA | Open a URL and return an indexed snapshot of the page's interactive elements. Automatically attempts WAAP challenges, including HUMAN/PerimeterX Press & Hold,
and dismisses common cookie/consent banners. No separate challenge command is needed.
If verification fails, navigation reports an error; do not assume clearance.
Set |
| snapshotA | Re-perceive the current page: a fresh indexed snapshot of its interactive elements (use after the DOM may have changed). |
| clickA | Click the element with the given index (from the latest snapshot). Returns the resulting snapshot (or a compact change summary when
|
| double_clickA | Double-click the element with the given index (from the latest snapshot). Use it for a control that opens or edits on a double click (a file row, an
inline rename). Two separate |
| click_atA | Click a point in the page, in CSS pixels (the same units as the
snapshot's Prefer |
| click_frameA | Click a point inside frame
|
| type_textA | Type |
| fill_secretA | Fill a field from an opaque secret capability. The capability names a registered provider and an opaque handle. It also binds the fill to exact origins, one field kind, an expiry, and a use limit. The tool never accepts or returns the secret value. |
| fill_vault_itemC | Fill a visible field from a vault item. The registered provider resolves the item inside Wraith. This tool returns
only |
| dragA | Press on element Use it for slider challenges ("slide to verify", puzzle sliders) and range
controls. Aim the knob with |
| press_keyA | Press one key or chord on the focused element: |
| select_optionA | Choose |
| upload_fileA | Upload local files through the file input or upload button at Each path must be inside a folder the server allows ( |
| go_backB | Go back one page in the tab's history. Returns the resulting snapshot. |
| go_forwardB | Go forward one page in the tab's history. Returns the resulting snapshot. |
| wait_forA | Wait until |
| scrollA | Scroll the page ( |
| browser_tabsA | Manage tabs. |
| save_stateA | Export the current session (cookies + localStorage) to a Playwright
storageState JSON at Set |
| readA | Return the current page's readable content as markdown (for extraction / summarisation, as opposed to acting on elements). By default only the main content (no site menus or footers); |
| network_requestsA | List the browser's recent requests: Filter by a URL substring ( |
| network_responseA | Return the response body of request |
| screenshotA | Capture a screenshot of the current page. Returns an inline PNG image (so a multimodal model can see the page and
disambiguate by the same element indices). On an SDK without image content
support, falls back to saving a temp PNG and returning its path. Wraith
blocks this tool after a secret fill. One image pixel is one CSS pixel, the
unit of the snapshot's |
| detect_waapA | Fingerprint a URL's WAAP / anti-bot defenses (Akamai, Cloudflare, Reblaze/Link11, DataDome, Incapsula, SiteMinder, reCAPTCHA, ...). Returns a list of detected vendor names — empty if none. Passive; no browser needed. |
| borrowA | Borrow a warmed, already-authenticated identity for
|
| ensure_high_scoreA | Borrow a logged-in Google identity's reputation and open This is the GENERAL reCAPTCHA-v3 pass: the v3 score is computed inside the google.com reCAPTCHA iframe from the .google.com reputation cookies present in the context, so injecting a warmed Google identity's cookies (delivered 3rd-party with secure+SameSite=None into an un-partitioned context) lifts the score across any sitekey/site. The browser is (re)launched with the un-partition firefox prefs, the reputation cookies are injected, then the URL is navigated (passing any WAAP and dismissing consent first).
WARNING: borrowing your primary Google identity carries anomalous-session / 2FA risk — this is opt-in. After it returns, VERIFY success against the real protected endpoint (accept vs reject); the v3 score is run-variable and there is no trustworthy score readout for a 3rd-party sitekey. Returns the detected reCAPTCHA params and whether the reload request carried the reputation cookies. |
| fetchA | No-browser TLS-impersonation request — the cheap fast path. Replays a captured session against |
| receive_profileA | Pull a synced login from a one-shot pairing A laptop runs |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 28 tools
Most tools have clearly distinct purposes, including the several click variants and identity-injection tools, which are differentiated by their descriptions. Minor overlap remains between borrow, receive_profile, ensure_high_score, and fetch, since all involve reusing authenticated sessions, but their intended use cases are distinguishable.
All tool names use consistent lower_snake_case with no camelCase or chaotic mixing. The naming is mostly readable and predictable, though it mixes single verbs, verb_noun, and noun-phrase forms rather than following one strict pattern.
At 28 tools, the surface is heavy and exceeds the usual compact range, but the server spans browser automation, content extraction, network inspection, secret filling, and anti-bot/session workflows. Most tools appear to earn their place, though the count is high enough to add selection overhead.
The tool set covers core browser lifecycle operations, interaction, extraction, tabs, state export, network inspection, and advanced anti-bot/session workflows. Some gaps remain, such as explicit hover, JavaScript evaluation, download handling, or richer cookie/context management, but these are mostly workaroundable.