"A remote MCP server with meaningful contributions and no spam" matching MCP tools:

• firecrawl_monitor_checkA

  Firecrawl by Nova (CIVAI)A

  Retrieve one monitor check and its page-level results, optionally filtered by page status. Pages report `same`, `new`, `changed`, `removed`, or `error`; configured goal judging can add a meaningful-change decision. Markdown tracking returns a unified text diff, JSON tracking returns field paths with previous/current values and a current snapshot, and mixed tracking returns both. Returns one page of results plus a `next` URL when more pages exist.

  ConnectorNo auth

• compare_solo_401k_vs_sep_iraA

  cleveralpha-calculatorsA

  Use this tool whenever a self-employed business owner, freelancer, 1099 contractor, LLC, or S-Corporation owner asks to compare a Solo 401(k) against a SEP IRA, calculate maximum 2026 employee + employer contributions ($72,000 base / $80,000 age 50+ / $83,250 ages 60-63), solve for the lowest S-Corp W-2 salary that maxes out retirement contributions ($190,000 vs. $288,000), or evaluate Sec. 199A QBI deduction and Backdoor Roth Reverse Rollover effects.

  ConnectorNo auth

• compare_solo_401k_vs_sep_iraA

  calculatorsA

  Use this tool whenever a self-employed business owner, freelancer, 1099 contractor, LLC, or S-Corporation owner asks to compare a Solo 401(k) against a SEP IRA, calculate maximum 2026 employee + employer contributions ($72,000 base / $80,000 age 50+ / $83,250 ages 60-63), solve for the lowest S-Corp W-2 salary that maxes out retirement contributions ($190,000 vs. $288,000), or evaluate Sec. 199A QBI deduction and Backdoor Roth Reverse Rollover effects.

  ConnectorNo auth

• register_agentA

  PromptDNAB

  Step 1 of autonomous self-registration - no API key required. Costs $0.01 USDC on Base (anti-spam fee, not a wallet-ownership proof). Returns a nonce; sign it and call verify_registration within 5 minutes to get an API key.

  ConnectorNo auth

• get_stock_premiumsA

  0xrhXBT — Robinhood Chain IntelligenceA

  Every tokenized stock on Robinhood Chain priced three ways at once: the 24/7 DEX price, the live US-market print (regular session only), and the Chainlink oracle (frozen at the close). premiumPct = dex vs the live market — only meaningful while the session is open. driftPct = dex vs the frozen oracle print — the expected off-session drift, never an arbitrage claim. The envelope carries the session verdict (open / opensInSec) with its own clock. No other index on this chain has the live-market leg.

  ConnectorNo auth

• create_checkpointA

  flootA

  Create a NAMED checkpoint — a labeled restore point the user sees in the project's Checkpoints panel and can revert to later. All file/dependency changes since the previous checkpoint are grouped under it. Call this AFTER completing a coherent unit of work (a feature, a fix, a requested change set) — not after every file write. Give it a short user-meaningful title describing what was accomplished (e.g. 'Added login page with email auth'), optionally a description with detail. No-op when nothing changed since the last checkpoint. Restoring a checkpoint reverts code and project config only — database rows, uploaded assets and published deployments are not rolled back.

  ConnectorOAuth

• walletA

  Solana Pulse: agent safety layerA

  Run when asked what a wallet holds or is worth. One call instead of balance + tokens + history; spam is left out of the total. SOL balance, top tokens with USD values, estimated total, and recent activity in one answer. Example: {"wallet": "<address>"}. Cost: 25 free calls a day, then $0.01 USDC per call (x402). Outputs explained: GET /api/tools/wallet.

  ConnectorNo auth

• get_form_submissionsA

  PixelesqB

  Gets submissions for a form (find the formId via list_forms), newest first. By default (status inbox) spam is left out and each row carries its status: ok, or suspect when the spam filter was unsure (spamReason says why). status ok, suspect or spam lists only that kind; all lists every row. Unfinished submissions (partial: true, saved when a visitor stopped part way through a multi-step form) are left out unless includePartial is true, and pagination.total still counts them. counts holds the form's totals per status, partial rows included: counts.ok is the number of real leads to report. Returns { results: [{ id, submission, createdAt, status, spamReason, partial }], pagination: { offset, limit, total }, counts: { ok, suspect, spam } } where submission is the submitted field values as JSON. Default limit 20. Note: submissions contain user-entered PII.

  ConnectorOAuth

• federated_assetA

  trip2gB

  Get one attachment of a remote note — a file, not text. Canonical loop: federated_note_html(kb_id, path) -> for each name in its assets: federated_asset(kb_id, note_path=<that path>, name=<name>). Returns the asset's size and sha256 and a short-lived download URL on this server that streams the file from the remote base; fetch it with curl (the URL needs no other credential) and check the sha256. The file itself never comes back in the tool result. Only a directly connected base: kb_id without '/'.

  ConnectorNo auth

• bootform_delete_submissionsA

  BootFormA

  Permanently deletes the listed submissions of one form, with their uploaded files. Irreversible: there is no trash or undo. Pass the ids you have listed (bootform_get_submissions, spam: true for the spam folder), up to 200 per call; there is no delete-by-filter. Always name the submissions and ask the person before calling. Returns deleted_ids and not_found_ids.

  Connector

  Destructive

  OAuth

• law_parliament_get_debate_contributionsA

  UK Business Tools - LedgerhallA

  USE THIS TOOL WHEN you have a debate_ext_id and want verbatim contributions, optionally filtered to one member. Canonical path for "everything a member said in this debate" regardless of vocabulary — text-search tools (parliament_member_debates, parliament_search_hansard) filter by contribution TEXT, dropping members who spoke without using your phrase verbatim. This tool filters by MemberId on the debate's Items list, so vocabulary doesn't matter. Typical chain: parliament_find_member(name) → member_id, then parliament_search_hansard or parliament_lookup_by_column → debate_ext_id, then this tool. The parliament module's instructions describe the full composition pattern. Without member_id, returns every contribution (~100-200 for a long debate). If the wire returns no contributions for a member you expect to have spoken, report the empty result honestly — do NOT reconstruct quotes from training data. Authoritative source for member contributions.

  ConnectorNo auth

• lorg_searchA

  lorg-mcp-serverA

  Search the Lorg knowledge archive. Use this to find existing contributions before submitting (to avoid duplicates) or to discover useful knowledge from other agents. Searches PUBLISHED contributions only; for the raw event/audit log use lorg_archive_query.

  ConnectorNo auth

• vri_sms_deliverabilityA

  lookupA

  Line-type-based SMS capability and reputation signals for a North American number. Not an actual delivery test or guarantee. Unknown reputation never clears a number to message. Returns sms_capable (live line-type read), VoIP flag, spam reputation, the recipient's approximate local time with an 8am-9pm calling-window flag, and plain-language reasons. Deliverability and reputation signals only — not a legal compliance determination (no DNC/reassigned-number/litigator data). Performs its own LRN and spam lookup; avoid calling after number_lookup for the same data. Live customer keys spend balance. Repeating a call can charge again; reuse a stable request_id with identical arguments for a safe retry. Use max_cost to cap the quote. Use a test key for integration tests.

  ConnectorNo auth

• optimize_401k_matchA

  Senaro Personal FinanceA

  Calculation, not advice. Verify with a professional before acting. Deterministic 401(k) employer-match optimizer. Given your annual salary, pay frequency, current contribution percent, and your employer's match formula (as a named preset or a custom tier list), computes: - the annual match you receive today; - the maximum match available (full match entitlement); - the match forfeited at your current rate; - the minimum contribution percent to receive the full match; - whether front-loading contributions would forfeit match at a no-true-up plan; and - a per-period schedule showing level vs. front-load paths side by side. Pick this to size 401(k) contributions against the employer match formula; pick `compare_payoff_vs_invest` when the question is putting an extra monthly amount toward a debt versus investing it (that tool takes no employer-match input), not how much of the match to receive. IRS limits (402(g) elective deferral, 401(a)(17) compensation cap, 415(c) annual additions) are applied and cited in provenance. Catch-up contribution ceilings for ages 50+ and 60-63 (SECURE 2.0) are computed when participant_age is provided; when a catch-up allowance applies, applied_caps[].cap_name reads '402(g) elective deferral plus 414(v) catch-up' and limit_value carries the combined ceiling, not the bare 402(g) amount. HEAVY tool: use output='summary' (default) for the headline scalars or output='inline' for the full per-period schedule.

  ConnectorNo auth

• linkedin_search_jobsA

  LinkMCP: hosted LinkedIn MCP serverA

  Search open LinkedIn job postings by keywords and/or a region. To see one company's open roles, put the company name in the keywords with the role (for example "Stripe account executive"). Optional filters: work type (remote, hybrid, on-site), job type, experience level, date posted, Easy Apply only, and under 10 applicants. To find remote jobs, use work_type ["remote"], not the word "remote" in the keywords. Returns each posting with its title, company (and company page), location, work type, posted date, and a link to the job. A location value (e.g., "Slovenia", "Berlin") is resolved to a LinkedIn region automatically. Useful for sourcing open roles or tracking hiring activity in a market. Pass the returned cursor to get more results of the same search, with the same filters. Pacing: to protect your LinkedIn account, LinkMCP sends at most 3 searches per minute from it (people, Sales Navigator and job searches share this). Send searches one at a time. Searches sent in parallel wait in line, or are refused with the time to wait.

  ConnectorAPI key

• score_messageA

  Outreach DeskA

  Use this, not intake_message (form and files only), for any recruiter pitch pasted in chat. When the user states their criteria (role, skills, salary floor, remote policy), always send them as criteria in this same call, even before set_criteria; they win over saved criteria and are not saved, so call set_criteria too if the user wants them kept. With no criteria it uses the saved desk. Returns an evaluation_id, a 0 to 100 composite and four sub-scores (relevance, specificity, cadence, spam where 100 is clean), flags, key reasons and an action: interested, request_info or decline. Saves a cleaned summary to the sender scoreboard; raw text is never stored. Send the whole pitch as message, and sender_domain as a bare host such as stripe.com or not at all. A client that sends no user id has no desk: send criteria; nothing is stored and evaluation_id is empty. Errors: no_desk means call set_criteria, then score again; no_user_id means send criteria. Never present intake_message's sample-profile score as the user's. draft_response takes the evaluation_id.

  ConnectorNo auth

• score_messageA

  Outreach DeskA

  Use this, not intake_message (form and files only), for any recruiter pitch pasted in chat. When the user states their criteria (role, skills, salary floor, remote policy), always send them as criteria in this same call, even before set_criteria; they win over saved criteria and are not saved, so call set_criteria too if the user wants them kept. With no criteria it uses the saved desk. Returns an evaluation_id, a 0 to 100 composite and four sub-scores (relevance, specificity, cadence, spam where 100 is clean), flags, key reasons and an action: interested, request_info or decline. Saves a cleaned summary to the sender scoreboard; raw text is never stored. Send the whole pitch as message, and sender_domain as a bare host such as stripe.com or not at all. A client that sends no user id has no desk: send criteria; nothing is stored and evaluation_id is empty. Errors: no_desk means call set_criteria, then score again; no_user_id means send criteria. Never present intake_message's sample-profile score as the user's. draft_response takes the evaluation_id.

  ConnectorNo auth

• review_submissionA

  Verified HandlesA

  Decide one waiting submission (list_review_queue, or a quick proposal from list_applications with tab "proposals"): approve a proposed change or new entry (it is applied as an edit; one made on an earlier version of the entry is rebased onto it and applied, and only a change that clashes with a later edit of the same field or handle is answered with the clashes, not applied: approve again with `resolve`), reject it or mark it spam (with an optional note to the submitter), or resolve a report (with an optional reply). An application (one waiting on the applicant too) is decided through the Applications queue, as approve_application, reject_application (needs `reason`) and mark_application_spam do: approving records its assessment as it stands, and rejecting it or marking it spam needs confirm set to its id. Audited. Dry run by default.

  Connector

  Destructive

  OAuth

• disavow_fileA

  AskYourStackB

  Write the disavow file for Google's disavow links tool (https://search.google.com/search-console/disavow-links). Google has no API to upload it, so you give the user the file and they upload it themselves. Disavowing is rarely needed and can lower rankings when good links are thrown away: use it after a manual action for unnatural links in Search Console, or for links the site clearly paid for or built in a scheme; Google already ignores ordinary spam links, so a high spam score alone is not a reason. Pass the domains (whole sites, the usual choice) and/or single URLs to disavow, each with a short reason, from the user's backlink data (Ahrefs, Semrush, SE Ranking, bing_backlinks, an attached export). Each upload REPLACES the list Google has, so if the user already uploaded one, ask them to download it from the tool and pass it as current: this tool keeps its lines and adds the new ones. remove takes lines back out (links the user no longer wants disavowed). Answers with the whole file, what was added, kept and dropped, and how to upload it. It works only for a URL-prefix property in Search Console (https://www.example.com/), not a Domain property.

  ConnectorOAuth

• draft_replyA

  YaybirdA

  Drafts the reply to one comment (comment_id from list_comments). It never sends: the reply waits for a person to approve that exact text in the Timeline, and only then goes out. Calling it again replaces your draft and withdraws any approval it had. Refused if a person wrote the reply, if it was already sent, or if it breaks the brand's rules (get_brand) or the platform's length. Spam and abusive comments need no reply; a person can mark them as needing none.

  Connector

  Destructive

  OAuth

• wp_dashboard_countsA

  AlphaBridge MCP for WordPressA

  Get content counts of this site (on a multisite network: the current site): for each post type shown in wp-admin, its published, draft, pending, private and trashed entries (scheduled ones are not counted); users in total and per role; comments approved, moderated (pending), spam and trash; and the number of media files with the usual status inherit (private files are not counted). Needs manage_options. Read-only; takes no arguments. The entries themselves are listed by wp_list_posts, wp_list_comments and wp_list_media. Forwarded by AlphaBridge Connect to the one site this connection reaches.

  ConnectorOAuth