"Slack Bot with RAG Document Retrieval and Automated Response System" matching MCP tools:

• get_evidence_documentA

  Plumbline — a trust layer for LLM answersA

  Show ONE retrieved evidence document behind an answer you already received, addressed by that answer's correlation_id plus a document_id from its evidence_documents references. Returns the full stored document (title, body, metadata, embedding_text) with the retrieval rank and scores the answer recorded; never the raw embedding vector. Only documents the addressed answer actually recorded resolve: there is no fetch-by-id in general and no way to browse the store. Requires the persisted compliance log and the same session that produced the answer. Absent from the no-auth public demo.

  ConnectorNo auth

• get_utility_service_statusA

  Ardaro Agent Runtime UtilitiesA

  Check the selected service's current runtime readiness, input limits, pricing and retention before use. Returns service and details; ready=false means the underlying service is unavailable. Free cached runtime read; no external probe, payment, analysis or historical document retrieval. Use get_utility_example for a fixed integration sample instead.

  ConnectorNo auth

• siteborne_retrieve_verified_web_contextA

  SITEBORNE Utility NetworkA

  Retrieve and verify evidence from one public web URL using direct HTTP retrieval. Use when: the request is specifically about the content and provenance of a URL. Do not use when: evidence must be synthesized for a company (use siteborne_build_company_evidence_graph), extracted from an authorized document (use siteborne_extract_document_evidence_json), checked against an existing output contract (use siteborne_verify_agent_output), or the page requires JavaScript rendering (rendered retrieval is not available). Parameters: retrieval_mode must be direct; rendered is defined but unavailable and is rejected before any payment challenge, never substituted with direct retrieval. output_mode structured needs buyer_schema and field_selectors to be meaningful; redirect_policy and max_redirects bound redirect following; max_content_size bounds returned bytes; maximum_authorized_price only constrains payment and never changes retrieval scope. Behavior: open-world: a paid request performs bounded outbound HTTP retrieval of the target URL through a safe-egress boundary (private and loopback destinations are refused) and persists governed payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. Retrieval admission follows the governed runtime rate policy; no fixed public per-origin rate is promised. This service is currently production-disabled and rejects execution. Economics: exact price of $0.008 USD per request in direct mode; the payment challenge requires that amount and the charge settles at exactly that amount. rendered mode has a governed price of $0.029 USD but is not available: it is rejected before any payment challenge and never substituted. Failure: schema-invalid input and unavailable modes are rejected before any payment challenge; target-site errors, timeouts and unavailable retrieval return a structured MCP error and are never answered with a substitute result. Returns: normalized, source-attributed web context with verification and PCC evidence.

  ConnectorNo auth

• get_filingA

  HKEx FilingsA

  Download one HKEx document by its URL and read, page through, or search its text. ``link`` must be an HKEx document URL from search_filings (host ``www1.hkexnews.hk``); any other host is rejected. With ``extract=True`` (default) the response includes up to 30 ``tables`` and a window of extracted ``document_text``: ``max_chars`` characters starting at ``offset``. Long reports return ``next_offset``; call again with it to read the next window. Pass ``query`` to search the whole document instead: the response then lists up to 20 case-insensitive matches with their offsets and surrounding text, plus ``match_count`` — use a match offset to read that part. Set ``extract=False`` for size and content type only.

  ConnectorNo auth

• dataset.exportA

  FlexOrch MCPA

  Download all records from a built dataset as text (Step 5 — final step). Returns the complete dataset content as a UTF-8 string directly in the response — no file download or separate URL needed. Call get_job_status after build_dataset and wait for status='completed' before calling this tool. Use the dataset_id from that completed response. Format guide: jsonl = LLM fine-tuning, rag = LangChain/LlamaIndex chunks, csv = spreadsheets, md = human-readable, xml = structured interchange. Binary formats (parquet, hf) cannot be returned via MCP — export them from the FlexOrch dashboard directly. Args: dataset_id: Dataset ID from the get_job_status completed build response. format: Text export format — jsonl, csv, json, md, xml, rag. Default: jsonl.

  ConnectorNo auth

• fetchA

  Payments Law — EU payments legislationA

  Use this to open and cite an EU legislative provision found by search. Simple retrieval of one provision's text by its cite anchor id (e.g. "psd-2 Art 97"), with citation metadata. A provision longer than the response ceiling arrives in part, with metadata.complete false and a metadata.next_cursor that get_provision continues. Accepts only ids this service minted — free-text citations belong to resolve_citation. get_provision returns more: paging, applicability and typed warnings.

  ConnectorNo auth

• tradebasis_research_libraryA

  TradeBasis Automotive Appraisal MCP (US)A

  Search published TradeBasis US dealer research, BHPH (buy here pay here) economics and portfolio benchmarks, the experimental BHPH Macro Conditions Index and its methodology, public blog articles, and legacy briefs. No arguments lists the catalog. topic retrieves a document by ID/slug/title; topic + section retrieves a section or continuation part. query searches; optional limit is an integer 1–20 (default 5). These modes cannot be combined. Returns published Markdown tables, dated evidence, sources and qualifications, not new financial analysis. Long documents return an overview and section directory. Publication is rechecked on every retrieval; unverifiable sources return retryable errors, not cached article text. Blog access uses the public internet. Publication/update dates, CMS modification, data coverage and retrieval time are distinct. Structured output uses operation=list/search/get/section/invalid; retrieval includes the requested Markdown and publisher caveats. Unknown dates and coverage remain null. No search cursor is supported; use returned section/part IDs for long content.

  ConnectorNo auth

• siteborne_retrieve_verified_web_context_v3_candidateA

  SITEBORNE Utility NetworkA

  Retrieve and verify evidence from one public web URL using direct HTTP retrieval. Use when: the request is specifically about the content and provenance of a URL. Do not use when: evidence must be synthesized for a company (use siteborne_build_company_evidence_graph), extracted from an authorized document (use siteborne_extract_document_evidence_json), checked against an existing output contract (use siteborne_verify_agent_output), or the page requires JavaScript rendering (rendered retrieval is not available). Parameters: retrieval_mode must be direct; rendered is defined but unavailable and is rejected before any payment challenge, never substituted with direct retrieval. output_mode structured needs buyer_schema and field_selectors to be meaningful; redirect_policy and max_redirects bound redirect following; max_content_size bounds returned bytes; maximum_authorized_price only constrains payment and never changes retrieval scope. Behavior: open-world: a paid request performs bounded outbound HTTP retrieval of the target URL through a safe-egress boundary (private and loopback destinations are refused) and persists governed payment, audit, job and Workflow state; an unpaid request returns payment_required; a repeated identical request with the same payment is replay-protected and is not charged twice. Retrieval admission follows the governed runtime rate policy; no fixed public per-origin rate is promised. This service is currently production-disabled and rejects execution. Economics: exact price of $0.008 USD per request in direct mode; the payment challenge requires that amount and the charge settles at exactly that amount. rendered mode has a governed price of $0.029 USD but is not available: it is rejected before any payment challenge and never substituted. Failure: schema-invalid input and unavailable modes are rejected before any payment challenge; target-site errors, timeouts and unavailable retrieval return a structured MCP error and are never answered with a substitute result. Returns: normalized, source-attributed web context with verification and PCC evidence.

  ConnectorNo auth

• procurement.vendor-vettingA

  blindoracleB

  Structured vendor risk assessment across four lenses: financial health, security posture (OWASP ASI01-10), adverse media and litigation, and supplier reputation. Returns a 0-10 risk score, per-category findings, and red flags. Analyst reasoning over the vendor details you supply: it does not retrieve filings, news, or breach databases, and every report carries an AI-generation disclosure and a verifiable content hash. For an automated audit of a live agent system, see security.massat-audit. Refuses, with no charge, when ≥5 web sources incl. vendor's published terms cannot be fetched. (x402: $99.00 USDC per call)

  ConnectorOAuth

• read_channelA

  AccountHubA

  Read one Slack channel's recent message history (conversations.history) — `channel` accepts a channel/group id (C…/G…), a DM conversation id (D…), or '#name'. Read-only: it never opens or creates a DM, so a user id (U…) or 'me' is refused with an explanation — pass the DM's D… id instead (a search_messages hit's external_id 'D…:ts' carries it). A DM between two people is read with your own Slack permission (user-token im:history); a DM with the bot uses the bot token; channels are unchanged. Pass `account` when more than one Slack workspace is connected (see list_accounts). Needs channels:history/groups:history/im:history/mpim:history — workspaces connected before this feature (or, for person-to-person DMs, before user im:history was added) get a reconnect hint. Slack caps this method at 15 messages per request and 1 request per minute for every workspace (a Slack Marketplace-listing restriction, permanent here) — request small `limit` values rather than asking for hundreds at once, and don't treat a shorter-than-requested result as an error. A rate-limit failure names how many seconds until it should succeed; wait that long before retrying. Use a reply's `external_id` (`channel:ts`) with read_thread to see its replies.

  ConnectorOAuth

• create_conversationA

  AccountHubA

  Create a Slack channel, or open a DM / group DM. Pass `channel_name` for a CHANNEL (add is_private for a private one; user_ids then invites those people) — the app creates it, which also means the bot is already in it and can post right away. Pass ONLY `user_ids` for a DM (1 id) or group DM (2-8 ids): that path uses the CONNECTING PERSON's token on purpose, because opening a conversation with the bot token would create a DM with the app instead of between the humans. Returns the channel id to use with send_message. Creating a channel is visible to the workspace — confirm the name with the user first. Needs channels:manage / groups:write (channels) or the user-token im:write / mpim:write (DMs); a workspace connected before 2026-08-28 returns a reconnect hint.

  ConnectorOAuth

• search_my_document_contentsA

  X1 WealthA

  Search the text (body contents) of the connected person's own documents in X1, such as trusts, policies, agreements, and K-1s, when they ask what their own documents say. Returns the matching passages with document and page, sheet, or section so you can answer from them and cite the page; it does not write the answer itself. To search by document name, title, or tag instead, use the document metadata search if one is offered. To compare known files, pass up to 10 authorized documentIds in one request instead of parallel per-file calls. all_requested coverage requires a matching passage from every selected document; best_effort can return partial evidence. Neither is a complete page-by-page review. If rate-limited, wait for outstanding searches and retry one at a time. Indexing is asynchronous after every save; a just-saved document may return an honest still-indexing state with an instruction to try again shortly. Governed retrieval contract: x1-vault-v1.

  ConnectorAPI key

• update-workflow-execution-assigneesA

  TestChimpB

  Change the assignee and/or CC list of a workflow execution. The caller (OAuth user, or the bot's owner with --bot) must be the current assignee or an org admin (admin override needs OAuth, not --bot); anyone on the team may assign an unassigned execution, and a CC'd user may remove themselves. 409 means someone else changed it: re-read with get-workflow-execution and retry. Assignee / CC accept team member user ids or emails. New assignees and CC'd users get a workflow-execution-assigned bot event plus email/Slack per their notification settings. Only call after the user explicitly approved the change. Returns the updated execution.

  ConnectorAPI key

• check_policyA

  Policy PalA

  Read one privacy policy or terms-of-service page and return a grounded verdict, eight fixed yes/no/partly/not-stated answers, and up to five findings, each with a verbatim quote from the document. Use this instead of fetching and reading the page yourself. A policy page is 20,000-60,000 tokens of context, and many are rendered by JavaScript so a plain fetch returns an empty shell without saying so. This returns about 1,000 tokens: a 20-60x saving with a quote behind every claim. Guarantees: every claim carries a verbatim sentence from that document, and a question the document does not address is answered not_stated -- never as a promise the document did not make. The eight questions are identical across services, so two reports can be set side by side. A report may be served from an earlier reading of the same document, which is what makes it cheap and instant. readAt says when that reading was taken; call policy_changes_since if it matters whether anything has moved since. Do not use this for a document that is not a legal agreement; it is refused, and a refusal costs nothing. Do not use it to summarise a page in general, to read a document the user pasted rather than published at a URL, or for legal advice: Automated reading of one document. Not legal advice.

  ConnectorNo auth

• engram_smarterA

  EngramA

  Brief a materially different task within the same session. Returns Markdown with ranked workspace/public memory, retrieval hints and optional checklists. Use engram_start for a new session, engram_rehydrate for lost context, engram_recall for one question, and engram_get_context for a category audit. context states the whole goal; repo/file focus retrieval without reading local files. limit overrides depth; include_skills=false suppresses checklists. Records retrieval/session telemetry without editing knowledge. Consumes workspace daily call quota. OAuth: memory:read.

  ConnectorOAuth

• slack_channel_refreshA

  Perspective AIA

  Refresh a workspace's Slack channel directory from Slack and wait for it. Only needed when a channel can't be found via slack_channel_search / slack_channel_resolve — most channels (including newly created ones and channels the bot was just invited to) are indexed automatically within seconds, so try those first. A full refresh can take a while on large workspaces, so confirm with the user before running one (unless a resolve reported "refresh_required"). Behavior: - Starts a refresh, or joins the one already running for the workspace (only one runs at a time). - Long-polls up to wait_ms, then returns "running" — call slack_channel_refresh_status to keep waiting (it won't start a new crawl). - After "completed", use slack_channel_search / slack_channel_resolve to find the channel.

  ConnectorOAuth

• get_store_template_detailsA

  agentViewA

  Returns full details of one store template: localized title and description, long-form markdown, category, suite, tags, features, preview image and agentArtifacts (bot-onboarding files such as system prompts, Agent Skills SKILL.md, MCP config). Use after search_store_templates before recommending or installing; when agentArtifacts is non-empty, fetch bodies via get_agent_artifact. No authentication required.

  ConnectorNo auth

• read_messagesA

  FlowCastleA

  Read the message transcript: what users sent the bot and what the bot sent back, newest first. Source is the runtime's own message ledger, written by the bot as it handled each turn — inbound messages are recorded before any routing decision, so messages that matched no trigger are here too. Filter by contactId for one conversation, botId for one channel, direction for one side, actor_type for who wrote it (contact / bot / agent — a human replying from Live Chat or over mail), and startDate/endDate for a window. Page further into the past by passing the returned nextCursor back as `cursor`. Text only. A photo or document contributes its caption; the file is not stored. Button taps are NOT messages and never appear here — use get_contact_activity for those. Message wording is redacted after the content retention window (the response says how long), leaving text null on old rows. Read-only. Requires the view_logs permission: this is raw personal message content of your end users.

  ConnectorNo auth

• list_bot_rentalsA

  Saylor Innovations: pay-per-call dataA

  Trading bots available to rent for a fixed period, with prices and durations. The renter runs the bot themselves with their own exchange key or wallet — nothing is hosted and no credentials are sent to this server. Free to call. Note: no performance or profitability data exists for these bots, so none can be reported; automated trading risks total loss of the funded amount.

  ConnectorNo auth

• workbench_kb_searchA

  ZeroWidth WorkbenchA

  Retrieves the most relevant chunks from one knowledge base — the core RAG primitive. `mode:"semantic"` (default) embeds the query and ranks by meaning (spends a small amount of workspace credit); `mode:"keyword"` is a free case-insensitive substring match. Each hit carries the chunk text, its document, and a score (cosine similarity 0-1 for semantic, match count for keyword). Get a kbId from `workbench_kb_list`.

  ConnectorNo auth

• workbench_kb_searchA

  ZeroWidthA

  Retrieves the most relevant chunks from one knowledge base — the core RAG primitive. `mode:"semantic"` (default) embeds the query and ranks by meaning (spends a small amount of workspace credit); `mode:"keyword"` is a free case-insensitive substring match. Each hit carries the chunk text, its document, and a score (cosine similarity 0-1 for semantic, match count for keyword). Get a kbId from `workbench_kb_list`.

  ConnectorNo auth