Skip to main content
Glama
821,831 tools. Updated 2026-11-22 17:32

"MCP server browser and installer for Glama platform" matching MCP tools:

  • Generates a browser authorization URL for connecting a new social account to a project. Flow: 1. Call this tool with the `projectId` and target `platform`. Omit `redirectUrl` unless the user asks for one. 2. Give the returned `url` to the user and ask them to open it in their browser and complete the authorization. 3. Once the user says they are done, call `social_accounts_list` with the `projectId` to confirm the connected account. For Facebook, WoopSocial shows a page-selection screen after authorization. The selected pages are connected to the `projectId`.
    ConnectorOAuth
  • Create a new ad group under a campaign. Every ad group belongs to one platform (body.platform, a platform id such as google-ads): only that platform receives it, its ads and its keywords. Leave it out on a campaign that runs on one platform; name it on a campaign that runs on several (400 AD_GROUP_PLATFORM_REQUIRED lists them). It is fixed once created — use copy_ad_group to run the same ads elsewhere. Returns the full updated/created object. Scoped to the active Space — see set_active_space to switch, or pass space_id to override for this one call.
    ConnectorAPI key
  • List and filter the CRM contacts (people who have written to or interacted with the connected accounts), each with `id`, `name`, `email`, `tags`, `subscribed` and `platform`, plus `count` with the total that matched before the limit. Use it to find a person or a segment; for one person's channels, custom fields and notes use get_contact, and for their messages list_conversations. Returns 40 by default and at most 200: if `count` is higher, narrow with tag, search, platform or accountId. The `id` is what get_contact, update_contact, set_contact_field and enroll_in_sequence take.
    ConnectorOAuth
  • Returns the social accounts this aicut user has connected for publishing, with the id `prepare_post` takes, plus `connect_url`. WHEN: before any posting attempt, and whenever the user asks where they can post. Each entry carries its `platform` (tiktok, youtube or instagram) and `schedule_custody` (`aicut_scheduler`: a scheduled post waits in aicut; `platform`, i.e. YouTube: the video is uploaded at once as private and YouTube publishes it, so a scheduled YouTube post can only be changed in YouTube Studio). IF THE LIST IS EMPTY the user has connected nothing: connecting is a browser sign-in this API cannot do for them, so give them `connect_url` and stop (do not retry or offer to post anyway). THIS TOOL SUCCEEDING DOES NOT MEAN THE USER CAN POST: it needs read permission only, while `prepare_post` and `publish_post` need `social:publish`. A 403 from `prepare_post` right after this call returned an account is the missing publishing permission, not a contradiction and not a bad account id (see its REFUSALS). Read-only: posts nothing, spends nothing.
    ConnectorOAuth
  • Use this when the user wants the numbers for their posts: "how are my clips doing", "which TikTok took off", "how many views did my Short get", "show my scheduled posts". Returns per post the platform, status, post URL, caption, clip title, the latest views, likes, comments, shares and saves the platform sent (null = the platform sends no such count) and views at 1 hour, 24 hours and 7 days. platform: tiktok, youtube, instagram, ... or all (default). status filters draft, scheduled, posted or failed (empty = all; status "draft" lists the post_id that update_draft and delete_draft take). limit 1-50, newest first. Covers posts RipClip published or planned. Not for: a recap of the week (weekly_report), platform against platform (compare_platforms), what is growing fast (whats_taking_off) or follower counts (get_account_stats). Free and read only.
    ConnectorNo auth
  • Get visitors grouped by browser name (Chrome, Safari, Firefox, Edge, and others), ranked by visitors descending, for a date range. Names only: use get_breakdown with dimension browser_version for versions, get_operating_systems for the OS split, and get_devices for desktop versus mobile. Pass filter_browser to other tools to scope them to one browser. Rows carry value, visitors, revenue, and percentage with pagination.total. Dates default to the last 30 days; all filter_* arguments apply. Requires websiteId or domain with a workspace token.
    ConnectorOAuth

Matching MCP Servers

  • A
    license
    A
    quality
    B
    maintenance
    Daily-refreshed Glama TDQS score tracker for any MCP fleet. Scrapes per-tool grades from glama.ai, stores in SQLite with snapshot history and delta tracking, surfaces via MCP tools, Prefab cards, a 6-page web dashboard, and an LLM-powered chat interface.
    7
    3
    MIT
  • F
    license
    A
    quality
    D
    maintenance
    Gives Claude control of a real, headed Chromium browser via Playwright, enabling web navigation, clicking, typing, screenshots, and JavaScript evaluation.
    8
    -

Matching MCP Connectors

  • A real Chromium browser agents can pay for per action over x402 (USDC on Base): navigate $0.005, extract $0.005, accessibility snapshot $0.005, act $0.01, screenshot $0.02, close free. Also runs free self-hosted over stdio via npx @scriptmasterlabs/agent-browser. Six tools with structured error codes and a public receipts log. Source: https://gitlab.com/timothy.walton45/agent-browser

  • Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.

  • Per-post metrics for posts published inside the window, sorted by a metric or by publish date, paginated. Use it for "top posts", "which post got the most comments" and "how did post X do". Covers posts published through AdaptlyPost and posts discovered on the connected accounts; Google Business Profile posts are listed with null metrics, since that platform reports only location impressions; discovered posts have postId and postPlatformId set to null, while AdaptlyPost posts carry the postId used by get_post. Returns { posts, total, page, limit, hasMore }; each post has platform, publishedAt, title, thumbnailUrl, permalink, connectionId, accountName and metrics { views, likes, comments, shares, saves, clicks, impressions, reach, engagementRate, plus engagedViews, averageViewDurationSeconds and averageViewPercentage on YouTube }, with null for metrics the platform does not report. Sort by a metric for a ranked list (list_top_posts returns the top few in one call); PUBLISHED_AT (default) for a chronological review. Not for publishing status: use list_post_results for that.
    ConnectorOAuth
  • Delete a post from iHatePosting. ONE SEND AT A TIME: a SCHEDULED post going to several accounts is stored as one post PER SEND, so deleting one cancels only that platform and leaves the rest scheduled — pass the `postId` that create_post returned on that particular send, or the id of the row list_posts shows for it. There is no need to cancel a whole multi-platform post to drop one platform from it. A DRAFT IS DIFFERENT: until it is scheduled, a draft is ONE post holding every platform it is aimed at (all its sends share one postId), so deleting it removes every platform — to drop one platform from a draft, use update_post with the remaining accountIds instead. The reply's `platformsRemoved` names every platform the delete took; for one send of a group, `stillScheduled` lists the sends still going out and `otherSends` the rest of the group (already published or failed), each with its status; their `scheduledAt` is UTC (it ends in Z) and `scheduledLocal` is the same moment in the account owner's timezone — report that one. THIS DOES NOT UNPUBLISH ANYTHING: a post that has already gone out stays live on the network, and deleting it here only removes iHatePosting's record of it. For that reason a published post is refused unless you pass force: true, and you should only do that after telling the user in words that the platform post will remain. A post that is publishing at this moment is never deletable, forced or not — the worker is mid-flight on it. Deleting a scheduled post stops it going out.
    Connector
    Destructive
    No auth
  • Aggregate performance for one connected channel, or for every channel at once. Returns impressions, reach, likes, comments and engagement rate for the period, the change against the preceding period of the same length, and the follower series. Omit `platform` for a team-wide total; pass `platform` (plus `channelName` or `providerId` from list_connected_accounts when that platform has more than one account connected) to scope it. `providerId` still identifies the account after its handle changes. `period` is 7d, 30d, 90d or all, defaulting to 30d. Use this for "how did LinkedIn do this month?"; use get_post_metrics for a single post and get_best_time_to_post for scheduling.
    ConnectorAPI key
  • Mints a single-use connect URL for Spicrawl's remote browser (GET /v1/browser, a DevTools Protocol (CDP) WebSocket) so YOUR code can drive it with any CDP client, using the URL as the browser WebSocket endpoint. It calls POST /v1/browser/token and returns a ws:// or wss:// URL carrying a short-lived token, never the API key: the URL works ONCE, within 60 seconds, and only with the options given here (editing them in the URL is refused), so call this right before connecting and again for every new session. Prefer sending the key as an Authorization header when the client supports headers on the WebSocket upgrade: then connect to the plain /v1/browser URL with 'Authorization: Bearer <key>' and no token is needed. The key must carry the `browser` scope. Parameter errors are reported when minting. The result's `session_id` names the session once connected: when a page needs a person (a login, a one-time code, a captcha), pass it to spicrawl_browser_live_view for a link they can open, and to spicrawl_browser_control to see when they hand control back.
    ConnectorAPI key
  • Metrics for this workspace's published posts. Returns a summary totalled across every published post (post count, overall totals, totals per platform), plus the newest posts in detail, each with one entry per platform it went to: impressions, reach, views, likes, comments, shares and saves. A metric is null when that platform does not report it; supported=false means nothing can be read for that target (no analytics for the platform, or no post id yet). Values are the last stored reading, not a live fetch, and fetchedAt says when it was taken. Use this to answer whether posts worked. It covers published posts only: use list_posts for drafts and scheduled posts, get_post for one post's details, and get_link_in_bio for visits to the link-in-bio page.
    ConnectorAPI key
  • Use to inspect the public IPv4 or IPv6 address observed for the connection making this MCP tool call. Takes an empty object and returns ip and family. This is the MCP client connection: a hosted AI client may observe its own exit address, not the user device address. If the user needs their browser or computer connection, direct them to the web tool or a CLI running on that machine. A VPN or proxy changes the observed path. One call observes one address family; it does not discover private local addresses, an address before a proxy, or both address families. The application does not store or log results, and no firewall rules are changed. Cloudflare Worker subrequests can have platform-specific address semantics; the result is not an identity proof. Operational events record the tool name, success or error, a controlled error code, and a traffic source classification. Verified automated checks may also record an automation run identifier. Events exclude inputs, results, raw request headers, and automation tokens. Cloudflare may attach platform metadata. Privacy policy: https://packetrove.com/privacy.
    ConnectorNo auth
  • List Agentropolis platform features with status (live, partial, stub, planned), endpoint and guardrails: badges, the x402 relay, seller claims and analytics, sponsored placement, market data, billing. Use it to check whether a platform capability exists before relying on it; it describes Agentropolis itself, not listings. Read-only, no parameters. Stub endpoints answer HTTP 501; payments_enabled shows whether Agentropolis charges for anything (currently false).
    ConnectorNo auth
  • Read back the rendered body of a version: the same bytes a reader receives in the browser, which differ from the uploaded file only by the one platform line <script data-space-sdk> — not a rewritten copy. This is how an agent confirms for itself that what went live is what it made: no browser, no screenshot, no human login, and no need to hand the link to the user to look at for you. Reads the entry file by default; pass file with a package-relative path to read one text file (.html, .md, .txt, .json, .svg and the like). To see which files a version has, and which one is the entry, read get_version artifacts. Two things it cannot read: PDF and PPTX content, which is page images (use preview_url, or the page count from get_version), and versions still uploading or converting, which have no body yet. A version in another workspace is not_found. A long body is returned up to a limit, and the reply states the full character count and whether it was cut.
    ConnectorAPI key
  • Find the data sources an account can put on a dashboard, across every platform it has connected. Use when: the user wants a source on a dashboard and you have no sourceId for it — search first, then pass what comes back to add_data_source_to_dashboard. Searches two things. Sources DashThis already holds are found straight away, whatever the platform. Sources that exist on the platform but nobody has picked yet are found only once the search names ONE connection — asking every connection would mean calling every platform — so pass 'connection' (or an 'integration' the account has only one connection to) when the first search comes up short. Returns: each source with its connectionId and providerKey, plus a sourceId when it is already set up; and the connections searched, so you can narrow to one. Rules: this creates nothing and changes nothing. If several sources could be meant, put them to the user and let them choose — never guess, because the wrong one puts another client's numbers on a report. Then: name the source, its platform and its connection when you report back — one client often has several accounts on the same platform — and its status when it is in error.
    ConnectorOAuth
  • Add a platform (or another account on a platform) to a Note that is already scheduled, so it posts there at the same time as the Note's other versions. Use this, not schedule_note, whenever the writer wants an already scheduled Note to also go to X, LinkedIn, Bluesky, Threads, Instagram, Facebook, TikTok or Pinterest: schedule_note would create a separate Note. Pass the id of any scheduled version of the Note (from list_scheduled_items, list_notes or schedule_note) and the platform. Without content the text is taken from the Note's versions (the same platform's version, else the longest that fits) and, if every version is too long, shortened to fit with adjustedPlatforms and warnings returned; content you pass is sent as written and must fit the platform's limit. When the writer has several accounts on the platform, name one with accountId (list_social_accounts; list_instagram_destinations for Instagram; list_linkedin_destinations for LinkedIn, with linkedInOrganizationUrn for a Company Page); without one the call is refused with the accounts to choose from. Ask the writer, never pick. Refused when the Note already goes to that platform or account (or posted there in the last day), when its time has passed or changed, or for Substack. Returns the new version(s) and their scheduled time. Safe to retry: pass a clientRequestId and reuse it only when retrying the same add (same Note and time, platform, account and content); a repeat returns the version already added (replayed: true), and the id reused for any other add is refused. Personal account only.
    ConnectorOAuth
  • Changes the signed-in person's data in the Dapper platform; needs a browser login, not an API key. Adds a bill to **this user's** watchlist in the Dapper platform — the same list list_my_followed_bills reports, and the same one they see in the dashboard. Use it when someone asks to follow, track or watch a bill. `notify=true` (the default) also turns on notifications for it; `notify=false` follows it quietly. There is a cap per account. Hitting it returns `FOLLOW_LIMIT_REACHED` with how many they follow today — retrying will not help, something has to be unfollowed first. The change lands immediately, but list_my_followed_bills reads a replica that trails by a few seconds, so a read right after may not show it yet.
    Connector
    Destructive
    API key
  • Changes the signed-in person's data in the Dapper platform; needs a browser login, not an API key. Adds or removes entities, commissions and sectors from **this user's** interest profile — what `dapper://me` reports and what personalises calls made without filters. **This adds and removes; it does not replace.** Pass only what changes: `add_entity_ids=[1635]` adds that one and keeps the rest. The platform stores each of these as a whole set, so this tool reads the current one, applies your change, and writes it back. `replace=true` wipes everything not listed and has to be asked for explicitly. Discover ids with list_entities and list_commissions. Interest **tags** are deliberately not editable here: 5 accounts out of 273 have any, while entities, commissions and sectors are what people actually filled in.
    Connector
    Destructive
    API key
  • Change an existing draft or scheduled post: its publish time (post_at), its caption, per-platform captions, or its status (draft or scheduled). Fields you omit are left as they are. Call get_scheduled_post first to see the post's targets and captions. For a post with one platform, pass caption. For a post sent to several platforms, pass captions with one entry per platform to change; platforms you leave out keep their caption. If a post has two targets on the same platform, identify each by target_id (listed by get_scheduled_post) instead of provider. Setting status to "scheduled" queues the post to publish at post_at to the connected social accounts. Published or in-progress posts cannot be edited and are rejected.
    Connector
    Destructive
    OAuth
  • Create a browser identity for a website the person must sign in to (or sign up on) themselves, and get back a link to give them. Opening the link shows a live browser on the site; when they have signed in they press 'I'm logged in, save session' and the identity becomes active, after which browser.open / browser.attach_identity work with it. Use browser.handoff instead for an identity that already exists and is active. For a plain username + password sign-in form WITHOUT captcha or 2FA, pass username, password and confirm_sign_in_stored=true and the platform signs in itself (admin or owner only): the answer is status 'active' on success, or the reason plus the human link when the site wanted more (a captcha, a code). When the site refuses the username or password, an identity created by this call is deleted again (status 'deleted'); one that already existed is left as it was. The password is kept encrypted in the workspace's secret store and used to sign in again when the session expires.
    ConnectorAPI key
  • Create a browser identity for a website the person must sign in to (or sign up on) themselves, and get back a link to give them. Opening the link shows a live browser on the site; when they have signed in they press 'I'm logged in, save session' and the identity becomes active, after which browser.open / browser.attach_identity work with it. Use browser.handoff instead for an identity that already exists and is active. For a plain username + password sign-in form WITHOUT captcha or 2FA, pass username, password and confirm_sign_in_stored=true and the platform signs in itself (admin or owner only): the answer is status 'active' on success, or the reason plus the human link when the site wanted more (a captcha, a code). When the site refuses the username or password, an identity created by this call is deleted again (status 'deleted'); one that already existed is left as it was. The password is kept encrypted in the workspace's secret store and used to sign in again when the session expires.
    ConnectorAPI key