MCP Tools: Analytics
Funnel, Kampagnen-Statistiken, ICP-Performance, Zeitverläufe, Qualifizierungs-Feedback — technische Referenz auf Englisch.
Technische Referenz auf Englisch.
Analytics
Funnel, campaign stats, ICP performance, timelines, qualification feedback
get_funnel
read-only
Get lead funnel overview (counts by status: pending, approved, contacted, replied, meetings, etc.).
No parameters.
get_campaign_stats
read-only
Get aggregate campaign stats (email: sent/opened/replied/bounced; LinkedIn: sent/connected/replied).
No parameters.
get_icp_performance
read-only
Get reply rates by ICP attributes (industry, company size, title, seniority).
No parameters.
get_playbook_stats
read-only
Get per-playbook statistics (companies, leads, approval rates, sequence performance).
No parameters.
get_timeline
read-only
Get daily activity timeline (leads contacted, opens, replies, meetings) for the last N days.
| Parameter | Type | Required | Description |
|---|---|---|---|
days | number | no |
get_reply_chains
read-only
Get detailed reply chain analytics with lead, company, playbook, and sourcing metadata. Shows industry, company size, buying signals, and channel breakdowns.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | number | no |
get_feedback_insights
read-only
Get AI-generated insights from pipeline feedback: what works, what doesn’t, and recommendations.
No parameters.
get_sequence_comparison
read-only
Get A/B test sequence comparison data: which sequences and variants perform better.
No parameters.
list_qualification_feedback
read-only
List qualification feedback history (ratings, reviews) for companies and leads. Useful for understanding what was accepted/rejected and why.
| Parameter | Type | Required | Description |
|---|---|---|---|
entity_type | enum(company \ | lead) | no |
entity_id | string | no | |
limit | number | no |
add_qualification_feedback
action
Add qualification feedback (rating + comments) for a company or lead.
| Parameter | Type | Required | Description |
|---|---|---|---|
entity_type | enum(company \ | lead) | yes |
entity_id | string | yes | Company or Lead ID |
rating | number | no | |
feedback | string | no | |
reason | enum(wrong_persona \ | no_budget \ | no_need \ |
qualification_status | enum(qualified \ | disqualified \ | needs_review) |
playbook_id | string | no |
Experiments
A/B tests, messaging angle experiments, variant comparison
list_ab_tests
read-only
List A/B tests comparing messaging variants across playbooks — shows variants, send counts, reply rates, and winner status.
No parameters.
create_ab_test
action
Create an A/B test from an existing sequence. Creates variant sequences with different copy.
| Parameter | Type | Required | Description |
|---|---|---|---|
sequence_id | string | yes | Original sequence ID to create variants from |
variants | object[] | yes | Variant definitions |
end_ab_test
action
End an A/B test by selecting the winning variant.
| Parameter | Type | Required | Description |
|---|---|---|---|
test_id | string | yes | A/B test ID |
winner_sequence_id | string | yes | Sequence ID of the winning variant |
list_messaging_angles
read-only
List all messaging angles — distinct narrative hooks used in outreach (e.g. pain-point, social-proof, ROI-focused). Each angle can be A/B tested.
| Parameter | Type | Required | Description |
|---|---|---|---|
persona_id | string | yes | Persona ID to list angles for |
status | enum(draft \ | active \ | testing \ |
create_messaging_angle
action
Create a new messaging angle — a distinct narrative hook for outreach (e.g. pain-point, social-proof, ROI-focused) that can be A/B tested against others.
| Parameter | Type | Required | Description |
|---|---|---|---|
persona_id | string | yes | Persona ID |
playbook_id | string | yes | Playbook ID |
name | string | yes | Angle name |
is_default | boolean | no | |
hooks | string[] | no | |
pain_points | string[] | no | |
value_props | string[] | no | |
objections | any | no | |
tone | enum(professional \ | casual \ | technical \ |
cta | string | no | |
proof_strategy | string | no |
create_experiment
action
Create a messaging angle experiment with a control and variant. Bootstraps a default angle if no control specified.
| Parameter | Type | Required | Description |
|---|---|---|---|
playbook_id | string | yes | Playbook ID |
persona_id | string | yes | Persona ID |
name | string | yes | Experiment name |
hypothesis | string | no | |
trigger_reason | enum(drop \ | plateau \ | anomaly \ |
variant_angle | object | yes | The variant messaging angle to test |
control_angle_id | string | no | |
traffic_split | number[] | no | |
min_sample_size | number | no |
approve_experiment
action
Approve a proposed experiment to start running. Sets variant angles to testing status.
| Parameter | Type | Required | Description |
|---|---|---|---|
experiment_id | string | yes | Experiment ID to approve |
edit_experiment_variant
action
Edit fields on a messaging angle used in an experiment.
| Parameter | Type | Required | Description |
|---|---|---|---|
messaging_angle_id | string | yes | Messaging angle ID to edit |
name | string | no | |
hooks | string[] | no | |
pain_points | string[] | no | |
value_props | string[] | no | |
objections | any | no | |
tone | enum(professional \ | casual \ | technical \ |
cta | string | no | |
proof_strategy | string | no |
end_experiment
action
End an experiment by selecting a winner or cancelling. Archives losing variant angles.
| Parameter | Type | Required | Description |
|---|---|---|---|
experiment_id | string | yes | Experiment ID to end |
winner_angle_id | string | no |
promote_angle
action
Promote a messaging angle to be the default for its persona. Archives the old default.
| Parameter | Type | Required | Description |
|---|---|---|---|
messaging_angle_id | string | yes | Messaging angle ID to promote |
get_experiment_results
read-only
Get experiment results with statistical significance analysis and projected days remaining.
| Parameter | Type | Required | Description |
|---|---|---|---|
experiment_id | string | yes | Experiment ID |
list_experiments
read-only
List all A/B test experiments with status (running, completed, paused), winning angle, and sample sizes.
| Parameter | Type | Required | Description |
|---|---|---|---|
playbook_id | string | no | |
persona_id | string | no | |
status | enum(proposed \ | running \ | completed \ |
check_experiment_triggers
read-only
Check if any playbook has enough data to automatically start a new A/B test experiment based on configured triggers.
| Parameter | Type | Required | Description |
|---|---|---|---|
playbook_id | string | no |
Feed
AI-prioritized recommendations, custom action types, execute or skip actions
get_recommendations
read-only
Get pending agent recommendations (prioritized actions for the SDR).
| Parameter | Type | Required | Description |
|---|---|---|---|
status | enum(pending \ | executed \ | skipped \ |
limit | number | no |
execute_action
action
Execute or skip an agent recommendation.
| Parameter | Type | Required | Description |
|---|---|---|---|
action_id | string | yes | The agent action ID |
decision | enum(execute \ | skip) | yes |
feedback | string | no |
get_lead_context
read-only
Get full context for a lead: profile, company, conversations, and pending actions.
| Parameter | Type | Required | Description |
|---|---|---|---|
lead_id | string | yes | Lead ID |
log_call_outcome
action
Log the outcome of a phone call with a lead.
| Parameter | Type | Required | Description |
|---|---|---|---|
lead_id | string | yes | Lead ID |
outcome | enum(meeting_booked \ | callback \ | not_interested \ |
notes | string | no |
batch_execute_actions
action
Execute or skip multiple agent recommendations at once.
| Parameter | Type | Required | Description |
|---|---|---|---|
actions | object[] | yes | Actions to process |
get_action_history
read-only
Get history of executed and skipped agent actions with feedback. Useful for learning what recommendations were useful.
| Parameter | Type | Required | Description |
|---|---|---|---|
status | enum(executed \ | skipped \ | auto_handled) |
channel | string | no | |
limit | number | no |
create_feed_action
action
Create a one-off custom action in the feed for a specific lead (e.g. ‘review contract’, ‘schedule demo’).
| Parameter | Type | Required | Description |
|---|---|---|---|
lead_id | string | no | |
type | string | yes | Action type key — use a built-in type (call_now, send_followup, crm_push, escalation) or a custom type registered via register_action_type |
priority | number | no | |
reasoning | string | yes | Why this action is recommended — shown to the user |
suggested_message | string | no | |
suggested_channel | enum(email \ | linkedin \ | phone \ |
agent_confidence | number | no | |
status | enum(pending \ | auto_handled) | no |
card_config | object | no | |
execution_config | object | no | |
metadata | object | no |
register_action_type
action
Register a reusable action type that can appear in the feed for any lead (e.g. ‘cold_call’, ‘send_case_study’). Use create_feed_action for one-off actions.
| Parameter | Type | Required | Description |
|---|---|---|---|
type_key | string | yes | Unique key for this action type (e.g. push_to_hubspot, approve_experiment) |
label | string | yes | Display label (e.g. “Push to CRM”) |
icon | string | no | |
color | string | no | |
description | string | no | |
execution_tool | string | no | |
execution_args_template | object | no | |
primary_action_label | string | no |
list_action_types
read-only
List all registered action types available in the feed. Use get_recommendations to see prioritized actions for specific leads.
No parameters.
delete_action_type
destructive
Delete a custom action type from this workspace. Cannot delete built-in types.
| Parameter | Type | Required | Description |
|---|---|---|---|
type_key | string | yes | Action type key to delete |
pause_lead_sequences
destructive
Pause a lead’s active outreach sequences. Optionally generates a farewell draft (stored in replies queue for approval, never auto-sent).
| Parameter | Type | Required | Description |
|---|---|---|---|
lead_id | string | yes | |
generate_farewell | boolean | no | |
reason | string | no |
Cost Monitoring
Monitor workspace spend (LLM + external services) and get ranked cost-optimization suggestions
get_cost_summary
read-only
Get the workspace spend summary over the last N days: total USD split into LLM (ai_usage_log) and external services (service_usage_log), plus breakdowns by model, source, service, pipeline step, and day. Use this to monitor where money goes.
| Parameter | Type | Required | Description |
|---|---|---|---|
days | number | no |
get_pipeline_step_costs
read-only
Get per-step pipeline costs (sourcing, research, qualification, enrichment, copy, outreach) from pipeline_step_costs, broken down by step, source, and day. Finer-grained drill-down than get_cost_summary; LLM rows here overlap ai_usage_log so do not add this to the summary total.
| Parameter | Type | Required | Description |
|---|---|---|---|
days | number | no |
get_cost_optimizations
read-only
Analyze workspace spend and return ranked, actionable cost-saving suggestions (model downgrades for routine work, oversized prompts, prompt-caching candidates, dominant services/steps) with estimated monthly savings. Returns the underlying summary too.
| Parameter | Type | Required | Description |
|---|---|---|---|
days | number | no |
Document Tracking
Track document/link engagement via PostHog
get_document_views
read-only
Get document/link engagement events from PostHog. Shows which leads opened tracked documents, how long they read, and which pages they viewed. Use this to identify engaged leads for follow-up.
Required integration: posthog
| Parameter | Type | Required | Description |
|---|---|---|---|
hours | number | no | |
document_name | string | no | |
lead_id | string | no |
get_tracked_link_events
read-only
Get all engagement events for a specific tracked document URL. Shows total views, unique leads, and per-lead engagement details.
Required integration: posthog
| Parameter | Type | Required | Description |
|---|---|---|---|
tracking_url | string | yes | The tracked link path or URL to look up |
CRM Intelligence
Closed-won deal signals + conversion patterns from the workspace CRM
list_crm_intelligence
read-only
List CRM intelligence signals (closed-won deals, conversion patterns) synced from the workspace CRM.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | number | no | |
since | string | no |
sync_crm_intelligence
action
Pull new CRM intelligence signals from the connected CRM (closed-won deals). Bounded by since + limit. Dedups on (crm, deal_id).
Required integration: hubspot
| Parameter | Type | Required | Description |
|---|---|---|---|
since | string | no | |
limit | number | no |
delete_crm_intelligence
destructive
Remove a stored CRM intelligence signal by ID.
| Parameter | Type | Required | Description |
|---|---|---|---|
id | string | yes |