"MCP feedback enhancement" matching MCP tools:

• rate_toolA

  IA-QA — 130+ QA & Dev Tools for AI AgentsB

  Give honest usage feedback on an IA-QA MCP tool. Provide a score (1-5) and a comment. Rate low (1-2) if the tool was wrong, irrelevant, or a poor fit; rate high (4-5) only if it genuinely solved your need. Ratings are aggregated on a public dashboard at /devtools/mcp-ratings. Skip rating routine successes — we want signal, not praise. Example: rate_tool({ tool_name: "format_json", score: 2, comment: "Tried to pretty-print a JSON5 file, it rejected trailing commas — not usable for my case." })

  ConnectorNo auth

• leave_feedbackA

  AgentMarketplaceA

  Leave feedback about AgentMarketplace itself — bugs, confusing tools, feature requests. This is for feedback about the platform, not about a counterparty. There is no reputation or rating system here — that lives in AgentTrust. Args: access_token: AgentAuth bearer token (requires ``market.read``). message: Free-text feedback, up to 2000 characters. Returns: ``{"recorded": true}`` on success.

  ConnectorNo auth

• feedbackA

  Media Generator — Images, Videos & AudiosA

  Save user feedback to the MultipleWords feedback API (POST /api/feedback). Call this only when a result has feedback_prompt.ready=true (the server asks after every 3 MCP runs — not per tool — and keeps asking until saved). Ask the user to pick a reaction and show the emojis: 😍 excellent, 😊 good, 😐 average, 😞 bad. Pass `reaction` (excellent|good|average|bad, or the emoji) and optional `feedback` comment text. If the user does not add a comment, omit `feedback` — the server stores the MCP name saifs_ai. After it is saved, wait for 3 more MCP uses. Do not invent a reaction. Do not send user_name, email, is_login, or app_id — those are injected server-side from the authenticated session. When showing the saved reaction, include the matching emoji. Args: reaction: User reaction. One of excellent, good, average, bad, or the matching emoji: 😍 excellent, 😊 good, 😐 average, 😞 bad. feedback: Optional short comment from the user. If the user does not add a comment, leave this empty. The server then stores the MCP name saifs_ai. Do not send the generation result or the user's question here.

  ConnectorOAuth

• send_team_feedbackA

  stubB

  Pass the entrepreneur's feedback, praise, complaint or feature request to the stub team, who read it in Slack. Use this whenever they ask you to send something on — "send this to the team", "tell stub that…", "can you report this", "they should fix…" — and offer it when they voice a clear frustration or want something stub cannot currently do. Quote their own words rather than summarising them. This is NOT feedback about the MCP tools (that is send_feedback), it does not open a support ticket, and nobody will reply in the chat — say so. ALWAYS check the returned `sent` field: when it is false the feedback reached nobody, and you must tell them it did not go through instead of thanking them for it.

  ConnectorOAuth

• feedbackA

  Marketing Intelligence & OptimizationA

  Save user feedback to the MultipleWords feedback API (POST /api/feedback). Call this only when a marketing_intelligence or marketing_intelligence_get_engine result has feedback_prompt.ready=true (the server asks after every 3 MCP runs — not per tool — and keeps asking until saved). Ask the user to pick a reaction and show the emojis: 😍 excellent, 😊 good, 😐 average, 😞 bad. Pass `reaction` (excellent|good|average|bad, or the emoji) and optional `feedback` comment text. If the user does not add a comment, omit `feedback` — the server stores the MCP name marketing_analysis. Do not send the analysis, test notes, or the user's question as the comment. Ask on the 3rd, 6th, 9th, … MCP run. Do not invent a reaction. Do not send user_name, email, is_login, or app_id — those are injected server-side from the authenticated session. When showing the saved reaction, include the matching emoji. When to call this tool: - User picks a reaction on the 3rd, 6th, 9th, … time this MCP is used - Collect a short comment plus 😍 😊 😐 😞 after an analysis - Save how the marketing analysis felt (excellent/good/average/bad) When NOT to call this tool: - Calling feedback before this MCP has been used 3 times - Asking after every tool call instead of every 3rd MCP run - Inventing a reaction the user did not choose - Passing user_name, email, is_login, or app_id (server injects them)

  ConnectorOAuth

• feedbackA

  Lead IntelligenceA

  Save user feedback to the MultipleWords feedback API (POST /api/feedback). Call this only when a result has feedback_prompt.ready=true (the server asks after every 3 MCP runs — not per tool — and keeps asking until saved). Ask the user to pick a reaction and show the emojis: 😍 excellent, 😊 good, 😐 average, 😞 bad. Pass `reaction` (excellent|good|average|bad, or the emoji) and optional `feedback` comment text. If the user does not add a comment, omit `feedback` — the server stores the MCP name lead_scoring. Do not send the analysis, test notes, or the user's question as the comment. After it is saved, the server waits for 3 more MCP runs before asking again. Do not invent a reaction. Do not send user_name, email, is_login, or app_id — those are injected server-side from the authenticated session. When showing the saved reaction, include the matching emoji.

  ConnectorOAuth

• batch_update_elementsA

  UnpagedA

  Move, restyle or rewrite many shapes at once, atomically — for restructuring a canvas after feedback.

  Connector

  Destructive

  OAuth

• submit_documentation_feedbackA

  docs-mcpA

  Send feedback about the Redpanda documentation or products directly to the Redpanda team. If the user hits a bug, a documentation gap, incorrect or missing information, or expresses frustration while using Redpanda, ASK whether they'd like to send feedback to the Redpanda team. Only call this tool once the user agrees — never submit feedback without their consent. When telling the user what will be sent, note that their work email and company domain are attached so the team can follow up. Summarize their feedback clearly and include the relevant documentation page URL or context when you know it. This tool requires the user to be signed in with a Redpanda Cloud account, because feedback the team cannot reply to is not useful. If the call is refused with authentication_required, the MCP connection itself is unauthenticated: tell the user to reconnect this server so their client runs its sign-in flow (signing in at https://docs.redpanda.com/login in their default browser first makes that hop quicker), and do not retry the tool until they have. Signing in on the docs website alone does not authenticate this connection.

  ConnectorOAuth

• feedbackA

  Synthetic Data — Random UserA

  Save user feedback to the MultipleWords feedback API (POST /api/feedback). Call this only when a result has feedback_prompt.ready=true (the server asks after every 3 MCP runs — not per tool — and keeps asking until saved). Ask the user to pick a reaction and show the emojis: 😍 excellent, 😊 good, 😐 average, 😞 bad. Pass `reaction` (excellent|good|average|bad, or the emoji) and optional `feedback` comment text. If they skip the comment, still call with `reaction` only — the server stores this MCP's name. Do not invent a reaction. Do not send user_name, email, is_login, or app_id — those are injected server-side from the authenticated session. When showing the saved reaction, include the matching emoji.

  ConnectorOAuth

• adsap_manage_ad_templateA

  AdsapA

  Create, update, or delete a saved Meta ad template (copy, CTA, destination URL, page/Instagram identity, pixel, catalog refs, enhancement toggles, site links). Completes the pair with adsap_list_ad_templates (read). Update is a PARTIAL PATCH — only the fields you pass change; the copy arrays (primary_texts/headlines/descriptions) and sitelinks replace their whole list. Enhancement toggles use the same toggle keys adsap_list_ad_templates returns in enhancement_flags. dry_run defaults TRUE: call once to preview the exact writes, confirm with the user, then call again with dry_run:false. Deleting a template does NOT touch launched ads; draft ad-sheet rows that still reference it are unlinked (the preview reports how many).

  ConnectorAPI key

• feedbackA

  Inventory Intelligence & OptimizerA

  Save user feedback to the MultipleWords feedback API (POST /api/feedback). Call this only when a result has feedback_prompt.ready=true (the server asks after every 3 MCP runs — not per tool — and keeps asking until saved). Ask the user to pick a reaction and show the emojis: 😍 excellent, 😊 good, 😐 average, 😞 bad. Pass `reaction` (excellent|good|average|bad, or the emoji) and optional `feedback` comment text. If they skip the comment, still call with `reaction` only — the server stores this MCP's name. Do not invent a reaction. Do not send user_name, email, is_login, or app_id — those are injected server-side from the authenticated session. When showing the saved reaction, include the matching emoji.

  ConnectorOAuth

• feedbackA

  Demand ForecastingA

  Save user feedback to the MultipleWords feedback API (POST /api/feedback). Call this only when a result has feedback_prompt.ready=true (the server asks after every 3 MCP runs — not per tool — and keeps asking until saved). Ask the user to pick a reaction and show the emojis: 😍 excellent, 😊 good, 😐 average, 😞 bad. Pass `reaction` (excellent|good|average|bad, or the emoji) and optional `feedback` comment text. If they skip the comment, still call with `reaction` only — the server stores this MCP's name. Do not invent a reaction. Do not send user_name, email, is_login, or app_id — those are injected server-side from the authenticated session. When showing the saved reaction, include the matching emoji.

  ConnectorOAuth

• submit_feedbackA

  ContinueOps Public MCPA

  Report that a public ContinueOps page or MCP tool response is incorrect, outdated, incomplete or confusing, so the team can fix it. Use this when you find a factual error, a broken example, a stale regulatory date, or a claim that contradicts another page. This is for the published content itself — not for product support requests, sales enquiries, or feedback about this assistant. Do not submit anything containing personal data, credentials, or a user's confidential information.

  ConnectorNo auth

• list_feedback_responsesA

  CharmingA

  Fetch unread Charming staff responses to feedback submitted by this authenticated account. Use this when a feedback-responses-available advisory appears. Responses are ordered oldest-first. Reading does not acknowledge them; call acknowledge_feedback_responses with the returned response IDs after processing them.

  ConnectorOAuth

• submitBuckyFeedbackA

  BuckyA

  Open a human-reviewed feedback form and submit it to the Bucky product team. Call only when the user explicitly asks to send feedback, report a problem, suggest an improvement, or praise something. The server asks the MCP client to show the form; nothing is saved unless the human accepts it. Do not use for silent agent self-reporting.

  ConnectorNo auth

• report-feedbackA

  docuwriterA

  Use this when the user explicitly asks to submit feedback about DocuWriter.ai or its MCP integration. After authorization, this state-changing action records the supplied feedback in DocuWriter.ai internal feedback logs.

  Connector

  Destructive

  OAuth

• enhancement_pathA

  Dali by LuluB

  Show the most reliable path from a bad grade to an A on this generator. Mines the Dali graph for all F/D → A/B enhancement pairs and surfaces the patterns that appear most consistently in the 'after' side. These are the highest-ROI moves for this specific generator. Use this when: - A prompt just scored D or F and you're not sure what to fix - You want to know which improvements matter most for a specific generator - You want to understand generator-specific enhancement strategy

  ConnectorNo auth

• upscale_videoA

  HermosoA

  Upscale a video to higher resolution (2x) for final delivery. Paid render; returns the served URL. Two engines: the default ('standard') is the safe precision upscaler; engine:'flux' is the FLUX 3 video upscaler (1080p/2K/4K) with an optional mode:'creative' detail-enhancement pass — pick it when the user asks for the FLUX upscaler or wants added detail rather than a faithful enlargement.

  ConnectorOAuth

• submit_tool_feedbackA

  Robot Actions — Remote Device ControlA

  Report feedback about the robot-actions MCP device-control tools THEMSELVES (not about the app under test). Use this to tell the maintainers when a tool was confusing, missing a capability you needed, behaved like a bug, or worked well and confirmed something you were unsure about. Be specific and actionable: name the tool_name, describe the concrete situation/inputs, and what you expected vs. what happened. This call is fire-and-forget — it is not shown to the end user, it only records feedback for maintainers to triage later.

  ConnectorOAuth

• send_feedbackA

  BilgA

  Send feedback (bug report, idea, other) to the Bilg team. Only call this when the user explicitly asks to send feedback to Bilg. Show them the final text first. Never include secrets, API keys or other people's data.

  ConnectorAPI key

• feedback-submitA

  hjarniA

  Submit feedback about Hjarni itself — confusing tool descriptions, missing capabilities, unexpected errors, friction, or praise. Use this when something about the MCP server, a tool, or the product behavior is worth flagging to the maintainers. Do NOT use this for the user's own notes or knowledge — those belong in notes-create. Required: category ('bug'|'confusing'|'missing_feature'|'friction'|'praise'|'other'), message (string, what's wrong and ideally what you'd expect instead). Optional: severity ('low'|'medium'|'high', default 'medium'), tool_name (the MCP tool the feedback is about, e.g. 'notes-update'), context (JSON-encoded string with any extra structured data — error excerpts, the arguments you tried, the steps that broke).

  ConnectorOAuth