Meticulate

Create one live company evaluation topic with a server-generated ID, without Calibration. Read get_config(company_targeting, full) first so the name is new and research-input topics and run-condition requirements reference current topics. Show the exact new topic and normally ask for confirmation; earlier explicit approval of this specific creation counts. Only then set user_confirmed=true. Requires org admin or team operator. Defaults match the app's Add topic dialog: generate when requested with no run conditions, basic firmographics, no web search (websearch_volume is 0 or 3) and 365-day regeneration timing. CRM-sync mappings are app-only. info_to_use.crm_fields must already be Pulled CRM Fields; add them with replace_pulled_crm_fields first. operating_locations is retired and rejected in standard_elements. Saves the definition only: no research, answers, record refresh, credits, enrollment or sending. To populate answers, run evaluate_companies afterwards; it previews cost and needs its own confirmation and credits. Names must be unique; read back before retrying an uncertain save.

Add one live Concept to a Ruleset without calibration, as the app's New Concept action does. Requires an org admin or team operator. Read get_config(requested_field="concepts") first so the new Concept does not duplicate an existing argument. It is appended to the end of the Ruleset's order and affects future drafting immediately. Not idempotent: repeating the call creates another Concept.

Start Targeting & Plays or Targeting & Sequences, optionally empty. Select up to five Plays or Sequences respectively. Targeting and the messaging framework are editable in both. Play dependencies are captured; selector-only Templates and Auto-Selectors are read-only. Sequence subjects default to the explicitly configured Standard set and are sampled only when Run is requested. An empty Standard set requires choosing test people; it is never populated automatically. Read get_calibration_guidance first. Use run_calibration_simulation for combined session testing.

Create one live ICP with a server-generated ID, without Calibration. No simulation. Read get_config(company_targeting, full) first so topic references and names are current. Show the exact new ICP and normally ask for confirmation before saving; existing explicit approval of this specific edit counts. display_name must be unique among the org's ICPs; tier (1-3) sets targeting priority and does not change which companies match. Requires org admin or team operator. Labels matching companies from existing evidence, without new research, persona evaluation, enrollment or sending. A retry with the same name is rejected as a duplicate, so read back before retrying.

Create a people list and optionally add up to 1000 existing org people.

Create a live person topic with a server-generated ID. Supports generated freeform text, single-select and multi-select topics, and manual number/text topics. With only name/description, retains legacy manual-text behavior. For configured topics, read get_person_topics first, confirm the specific live creation (earlier explicit approval counts), then set user_confirmed=true. Requires org admin or team operator. Set generation explicitly; it defaults off: generate_when_requested=false means the topic never generates, not "always generate". Use instructions.example_format for freeform answer shape. Person profile, company information and motion evidence are automatic. Only linkedin_posts is an optional standard input; other standard-element values are legacy and do not restrict stored context. Prior topic answers and CRM research fields remain explicit selections. Research inputs use the same PersonInfoElements as the app; CRM research fields must already be selected in Pulled CRM Fields. Dependencies must reference existing earlier topics. CRM-sync mappings are app-only. Does not evaluate people, populate answers, enroll, send or charge credits. Read back before retrying an uncertain save; duplicate names fail.

Create one live persona with a server-generated ID, without Calibration. No simulation. Read get_config(person_targeting, full) first so the new fit text complements existing personas instead of duplicating their strong fits. Show the name, tier and full definition and normally ask for confirmation before saving; earlier explicit approval of this specific creation counts. Set user_confirmed only after that approval. display_name must be unique among the org's personas; tier (1-3) sets targeting priority. Write the definition in the same Strong fit / Weak fit / Not a fit format as existing personas. Requires org admin or team operator. Existing people are not evaluated against the new persona until persona fits are updated in the app; this does not reclassify people, run research, enroll or send. A retry with the same name is rejected as a duplicate, so read back before retrying.

Create one empty Sequence owned by the authenticated user and return its ID. Use only when the user needs a new Sequence, not to edit an existing one. This saves an empty Sequence with no steps and does not activate prospecting. It is private unless share_with_org is true. Every sequence drafted from it uses ruleset_id (default: the user's default Ruleset, then the org default). Call once, then retain the returned template.id for subsequent editing; repeated calls create separate Sequences. In the in-app assistant, pass that ID to propose_template_changes for a reviewable AI proposal. Other MCP clients can populate the Sequence with update_sequence using the returned template_xml and updated_at.

Delete a company list, as Delete does in the app. Removes the list and its sidebar pins; the companies themselves are unaffected. Only call when the user explicitly asks to delete this list.

Delete a saved Company Searcher search, as removing it in the app's Searcher does. Only its creator or an org admin can delete it. It disappears from every listing and cannot be restored. Companies, lists and records found through it are unaffected. Only call when the user explicitly asks to delete it.

Permanently delete one live company evaluation topic without Calibration. Topics have no archive state. Read get_config(company_targeting, full) first and pass the topic's current definition as expected_topic; concurrent edits are rejected. Show which topic will be deleted and normally ask for confirmation; earlier explicit approval counts. Requires org admin or team operator. Nothing is deleted, and the dependents are named, while the topic is used by an active Audience, Play signal filter, user territory, Existing Solution, ownership routing rule, New Joiner scope, ICP definition or another topic's run conditions: change those first (for example with save_audience or replace_icp). Other topics that only use it as a research input have that input removed, as in the app. Archived Audiences and Plays keep the dangling filter and can't be restored until it is removed. Does not research, refresh records, enroll or send.

Delete one live ICP without Calibration, removing its company labels and Audience references. Read get_config(company_targeting, full) first and pass the ICP's current name, tier and definition as expected_icp. Show which ICP will be deleted and normally ask for confirmation; existing explicit approval counts. Requires org admin or team operator. The ICP is removed from Audience ICP filters that also list other ICPs. If an active Audience filters on this ICP alone, nothing is deleted and the Audiences are named: repoint them first with save_audience. Does not research, evaluate people, enroll or send.

Delete a people list, as Delete does in the app. Removes the list and its sidebar pins; the people themselves are unaffected. Only call when the user explicitly asks to delete this list.

Delete a saved people search, as removing it in the app's Searcher does. Only its creator or an org admin can delete it. It disappears from every listing and cannot be restored. People, lists and records found through it are unaffected. Only call when the user explicitly asks to delete it.

Permanently delete one live person topic, matching delete_company_topic. Topics have no archive state. Read get_person_topics first and pass the topic's current definition as expected_topic; concurrent edits are rejected. Show which topic will be deleted and normally ask for confirmation; earlier explicit approval counts. Requires org admin or team operator. Nothing is deleted, and the dependents are named, while the topic is used by an active Audience, Play signal filter, user territory, ownership routing rule, New Joiner scope or another person topic's generation conditions: change those first (for example with save_audience or replace_person_topic). Other person topics that only use it as a research input have that input removed, as in the app. Archived Audiences and Plays keep the dangling filter and can't be restored until it is removed. Does not research, recompute, enroll or send.

Delete one live persona without Calibration and remove its Audience references. Read get_config(person_targeting, full) first and pass the persona's current name, tier and definition as expected_persona. Show which persona will be deleted and normally ask for confirmation; existing explicit approval counts. Requires org admin or team operator. The persona is removed from Audience persona filters that also list other personas. If an active Audience filters on this persona alone, nothing is deleted and the Audiences are named: repoint them first with save_audience. Does not reclassify people, run research, enroll or send.

Add, update or remove one step in an existing Adaptive Step Bank. Read get_sequence first and supply its updated_at. For add/update pass one complete <bank-step> element in bank_step_xml, using the same XML syntax as get_sequence. Update replaces only that step, preserving its ID and position; bank_step_id is required for update/remove. An XML id must match bank_step_id when both are provided. Add appends; omit both IDs to generate a new one. Remove takes no XML. Other steps, metadata and shared Formats are preserved. The entire resulting bank is validated through the normal permission-checked, revision-guarded Sequence save. Returns the change summary, step inventory and new updated_at for the next edit; pass response_detail="full" to also return the saved bank XML. Does not enroll, send, or change existing drafted sequences. In-app assistants must use the suggested-changes workflow instead of this live-write tool.

Apply atomic, revision-checked draft edits, including Template/Adaptive content. expected_revision is the session-wide revision from read_calibration_working_copy, not the per-slice working_config_revision. Supports single-item/section edits, positional insert and exact-match text replacement. Edits apply in order: an insert or remove shifts later array positions. expected guards the current value or item text and is required to remove or replace a whole Ruleset block. No publication or testing. Destructive proposals require confirmation in the app.

Edit one Draft (lifecycle status proposal, shown as Draft in the app). Identify each step by step_index (1-based send position, as shown by get_sequences) or action_step_id. Pass only the fields to change. message edits email bodies or LinkedIn text; with message_format=plain_text an email body is written as ordinary text, converted exactly as written (include any signature yourself); **text** becomes bold and bare URLs or domains become links. subject edits email subjects; guidance edits phone call guidance. LinkedIn connection notes must fit 300 characters. Returns the Draft's ordered steps with short previews and which steps still need review; set include_full_sequence=true for every step field. Saves the Draft but does not approve it. For several Drafts at once, use edit_drafts.

Edit up to 25 Drafts in one call, each with the same step_edits shape as edit_draft. Drafts are saved independently: one failing Draft does not stop or undo the others, and each result reports ok or the error. Returns each Draft's ordered steps with short previews and steps needing review; set include_full_sequences=true for every step field. Saves the Drafts but does not approve them.

Find prospects at selected companies and match them to org-defined persona fits. Use this after get_companies, get_company_searches, or a company list gives you standard company IDs. Pass org_personas_to_find when the user asks to find existing target personas, persona fits, buyers, prospects, or the right people at a company. Use custom_persona_to_find only when the user gives a new freeform persona that is not one of the org's configured personas. Do not invent a custom_persona_to_find for broad requests like "persona fits" or "decision-makers"; use the org's configured personas. If the user seems to want a custom profile but has not specified it clearly, ask them to confirm the custom persona before running. Add found people to exactly one destination: either an existing people list via people_list_id, or a new people list via people_list_title. REQUIRES POLLING: call get_people with person_filters.list_id or get_lists(type='person') using the returned people_list_id.

Generate a quick preview of one saved Template for exactly one person. Supply person_ref from get_people (universe-person:<uuid>) or a LinkedIn URN. CRM/imported people without LinkedIn are supported using existing workspace context. person_linkedin_urn is a compatibility alias; supply only one of the two names. Save edits with update_sequence first. Uses the same preview execution path as the editor, including live prospect context. For an Adaptive Sequence, supply adaptive_format_id from list_adaptive_formats. The Format is validated before creating the preview session. Returns before generation finishes: poll get_sequence_preview with the returned template_id and session_id for status, complete message text, errors and staleness. This does not send, enroll, or make anything live. For a full multi-person simulation use create_calibration_session instead.

Read an exact Format, including an archived version. Does not follow successors.

Read a selected-person Draft batch, current sequence warnings and per-person outcomes. Read-only: never retries, enrolls or approves. Sequence warnings are the app's current proposal_warnings, separate from activation/skip warnings. Set max_wait_seconds (up to 300) to wait while people are still Composing; it returns as soon as the batch is no longer running. If status is still running, call again. Use get_sequences for full messages before explicit approval to send.

Read visible Audiences with membership counts from the latest refresh snapshot. Each row has parent_audience_id/name/revision, local filters, visible child_count and membership (member_count, company_count, snapshot_at, refresh_pending). Compact omits unset filter fields and inherited/effective filters; omitted fields are unrestricted, so compact filters can be saved back as-is. Full adds inherited_filters and effective_filters. Child filters only narrow the parent (AND). Save local filters, never copy effective_filters back into filters. Audiences define people independently of Plays and messaging; parent/child membership snapshots refresh independently. Archived Audiences are included with archived_at set.

Compatibility tool: prefer get_step_library_item. Internal users only. Adapt into independent customer-owned copy with fresh IDs through existing sequence authoring tools. Read construction guidance and the customer's Ruleset first. Replace example claims/metrics with verified customer facts; respect prior-message dependencies. This tool creates no customer content.

Read a live Auto-Selector's complete routing, metadata and revision. Discover IDs with get_options(requested_fields=["auto_selectors"]). Use this before save_auto_selector; preserve unchanged metadata and pass revision as expected_revision. No calibration session is required. Set include_archived=true to read an archived selector (archived_at set) before restoring it with set_auto_selector_archived.

Read ten frozen Audience/Play test receipts; pass next_before for older runs.

Read calibration orientation, sourcing/reuse/credit rules and worked examples before calibration planning, editing or interpreting results. No writes or simulations.

Read a durable simulation receipt after submission or a transport timeout. Submission is not completion. Repeating run_calibration_simulation with the same idempotency_key retrieves the original operation without new work. This response separates worker interruption from completed evaluations. lifecycle=finished means the attempt ended, not that every row succeeded. outcome distinguishes succeeded, finished_with_issues, and failed; null means no finished outcome. Freshness is independent and can be unknown. Per-run baseline/current counts separate old-comparison failures from current output failures. Legacy completed counts successful rows only; prefer succeeded and side counts. Never describe terminal failures as not simulated, and never count baseline failures as current draft failures.

Read a Make Live request and durable publication status. Pass both IDs returned by make_calibration_live. Poll until is_terminal. Only status=succeeded confirms publication. Request acceptance is not completion; failed/rejected requests must not be reported as live.

Read one Calibration Session. For a compact readiness summary, use review_calibration_session. For actual copy review, request simulation_results with surface="messaging": entries[].before_sequence/after_sequence contain COMPLETE subjects and bodies; *_details_preview fields are abbreviated and are not the copy. For company/person targeting evidence, request simulation_results with result_detail="full" and an explicit run_id. Optionally pass entry_id from a compact result to inspect one company/person. Full results return entries[].full_targeting_result with ALL saved answers, explanation bullets, sources, errors and available persona evaluation inputs. Full pages contain at most 3 entries; follow pagination for the rest. No new research is performed. Missing evidence or condition-level ICP decision traces cannot be reconstructed from data that was not saved. before_status/after_status distinguish not_run, in_progress, failed, incomplete and complete; running results are provisional, even when they already contain answers. Full results also expose saved config snapshots when available and per-entry before/after revision IDs. Use get_calibration_session when you need one specific piece of a session: status/latest_runs for progress and latest result pointers; messages/chat_history for the visible session conversation; working_config/base_config/diff with runbook for one editable config area; working_config_search with query to find text in working configs; template_sequence_targets for the full base and working Template copies attached to a Template session; strategy_target for the full base and working Strategy definition; simulation_results with surface for one paginated simulation-result set; calibration_summary only when the full summary text is needed. Broad working_configs/base_configs are supported, but can be large. Avoid broad combined reads for normal review workflows. For simulation_results, pass surface to choose company_targeting, person_targeting, or messaging. Use limit and offset to page through simulation result entries; those pagination parameters only apply to simulation_results. Compact reads default to the latest run for that surface; full targeting reads and entry_id require an explicit run_id.

Discover recent Calibration Sessions. Use this first for recent/latest/most relevant calibration sessions, then call get_calibration_session with the chosen session_id for details. requested_fields can include calibration_summary and run_summaries. Enriched calibration-list requests are capped at limit <= 3.

Read companies in an org. requested_fields can include standard_company, company_info, people, signals, exclusion, notes, heat_score, detailed_topic_answers, targeting_qa, account_research, and people_finding. Default rows are designed for broad targeting review: company identity, min-criteria status, targeting state, overview.icps, lightweight firmographics, and overview.topic_answers with one compact value per configured company topic. Use requested_fields=["targeting_qa"] when you need fit/non-fit reasons, ICP pass/fail details, and min-criteria context. Requested fields add nested sections and capped evidence. Heavy enriched company requests are capped at limit <= 3. Use company_filters to narrow by CRM, ICP/min-criteria, lists, owners, prospecting state, exclusions, company IDs, names, or topic answers. Omit it when no filtering is needed. count is the total matched row count; pagination.returned_count is the number of rows returned on this page. Default sorting prioritizes companies that look more ready for sequencing over alphabetical edge cases.

Read a company-list admission task and verify its requested memberships. Only reports IDs queued by this task, not immediate additions from the original call. present_count verifies current membership, not insert attribution. A completed task with an error outcome or missing IDs is not full success.

Read this user's platform-owner task. After completion, verify owners with get_companies.

Read saved Company Searcher searches and optionally include result pages. Without results, each search is returned as metadata with no result count. With results, count_accuracy indicates whether the count is exact, estimated, or capped.

Read one area of an org's configuration. Choose exactly one requested_field per call: org, company_targeting, person_targeting, rulesets, customer_stories, concepts, other_collateral, template_sequences, or calibration. Use compact detail for review/audit questions. Use full detail only when the user needs the complete text or structured body for that one area. The org field returns org/business and operational settings. company_targeting returns min criteria, company topics, ICPs, company search recommendations and company Pulled CRM Fields (pulled_crm_fields). person_targeting returns personas, person topics, person targeting filters and person Pulled CRM Fields (Contact or Lead record_type). Full targeting detail includes live topic prompts, research inputs, run conditions, and ICP/persona qualification definitions. Use full detail before recommending targeting edits; no Calibration session is needed. For approved live edits use create_icp, replace_icp, delete_icp, create_persona, replace_persona, delete_persona, create_company_topic, replace_company_topic, delete_company_topic, replace_person_topic, delete_person_topic or replace_pulled_crm_fields; use Calibration when testing or coordinated structural edits are needed. The customer_stories field returns live customer-story collateral. Customer stories and Other collateral include IDs and opaque content revisions. Use exactly one ID or unique label and expected_revision for single-entry updates/removals. Read full detail before editing text; compact previews can be truncated. Whole-section replacement requires the complete original entries as expected_entries. The concepts field returns complete live Concepts grouped by active Ruleset, including name, when_to_use, content, and frequency bias. Archived Concepts are excluded unless include_archived_concepts=true (rows then carry archived; restore with set_concept_archived). Both detail levels return complete Concepts; no Calibration session is required. The other_collateral field returns live Other collateral from the Knowledge Base. The template_sequences field returns accessible live Templates; full detail returns canonical template_xml with ordered steps, exact copy, slots, timing, and delivery settings. The XML can be passed directly to update_sequence after editing. The calibration field returns the org-level calibration summary and log. Full rulesets can be long, so their blocks are paged per item with block_offset and block_limit (1–100, default 25). Start with block_offset=0 and continue while any returned item has has_more_blocks=true. For rulesets or concepts, pass ruleset_id to read only that active Ruleset.

Discover tracked people/company filter schemas and valid workspace values. Request people_schema, company_schema or sequence_schema for the MCP contract with shared UX matching semantics, targeting for personas/ICPs/topics, or crm for field identifiers, data types, options and stages. Use get_motion_filter_options for Motion-specific IDs and refinements. Fetch only the section needed. Never invent IDs or unsupported fields.

Read sent and received prospect interactions. Use this for recent outbound activity, replies, prior touches, and account history. Returns subject/body previews, sending-account and email-address metadata, and thread IDs. Use outbounding_account_ids for sender-level volume analysis and thread_ids to audit a specific conversation. Returns all non-warmup activity. Use sources to restrict provenance; externally sent and CRM-imported activity is visible history, not platform execution. Legacy include_unassociated=false restricts history to platform activity, manually logged activity, provider messages, and samples; true or omitted includes CRM imports and system events too. Explicit sources take precedence. Incoming outreach attribution is no longer stored, so the legacy false scope cannot distinguish outreach replies from other provider messages. Set include_full_content=true to read the complete, untruncated message in full_content (including the email subject), rather than just previews. Filter by person with person_ids, or with person_ref/person_refs as returned by get_people.