GTM Vault MCP
Server Details
GTM operator evidence in Claude: layer audit, Build Your Stack, operator stacks, episode search.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 7 tools
Most tools target a distinct resource: search_vault (transcripts), list_operators/get_operator_stack (operators), list_playbooks/get_playbook (playbooks) form clear list-vs-get pairs. The only real overlap is build_stack versus run_layer_audit, since both take structured inputs and end at a stack build; the descriptions differentiate inputs and output shape well enough that an agent can choose, but the boundary is not razor-sharp.
All seven names are snake_case verb_noun (build_stack, get_operator_stack, get_playbook, list_operators, list_playbooks, run_layer_audit, search_vault). Verbs are used consistently for their intent: list for enumeration, get for single-resource retrieval, build/run/search for actions.
Seven tools is well within the sweet spot and each one covers a distinct capability (stack build, operator lookup, playbook lookup/list, audit, vault search). No redundant or filler tools are present.
Core workflows are covered: stack building, layer audit, playbook and operator retrieval, plus full-text vault search. The main gap is episodes as a first-class resource — there is no list_episodes or get_episode, so episode codes/links surfaced by search_vault can only be followed externally rather than expanded in-tool.
Available Tools
7 toolsbuild_stackBuild Your StackARead-onlyInspect
Build Your Stack from The Stack Index. Takes revenue band, motion, binding constraint and budget posture, and returns install order by layer: install first, install next, not yet. Every tool comes with the operators who run it, and the result includes a build_url that opens the same build on pro.gtmvault.co. Use for tool or stack recommendations.
Inputs: motion (required), revenue_band (required), budget_posture (required), binding_constraint (required).
get_operator_stackOperator stacksARead-onlyInspect
Look up operator stacks in The Stack Index. Pass operator to get one operator's full stack by layer with their episode. Pass tool to get every operator who runs that tool, what they use it for, and every displacement on the record (what it replaced, what replaced it). Use when the user asks what a specific operator runs, or who uses a specific tool and what alongside it.
Inputs: tool, operator.
get_playbookRun a GTM Vault playbookARead-onlyInspect
Get a GTM Vault playbook or skill by name, for example gtm-audit, tool-check or gtm-vault-caption-pack. Returns its steps and the tools each step uses. Any inputs passed are returned with the steps.
Inputs: name (required), inputs.
list_operatorsOperators on the recordARead-onlyInspect
List the operators on the record in The Stack Index, with their company, episodes and how many tools they named. Filter by layer, by tool, or by show. Use when the user asks who is in the index, who to learn from in a layer, or which operators run a tool. Returns operator names and slugs.
Inputs: show, tool, limit, layer_id.
list_playbooksList GTM Vault playbooksARead-onlyInspect
List the GTM Vault playbooks: multi-step workflows such as gtm-audit, build-my-stack, tool-check and decision-memo, plus the Skills group: operator skills built from systems on the record (PQL scoring, review signals, account monitoring, win-loss, Claude Code outbound, cold email, MCP enrichment, agents behind the rep, revenue intelligence, AI search citation, BDR intent action layer, browser enrichment actions, headless AE dashboard, LinkedIn outbound with Loom demos, niche down to expand, GTM engineer rollout on Clay, revenue context layer, self-learning support loop) and the operating skills GTM Vault itself runs on (episode write-ups, trailer briefs, thumbnails, the signals and AI citation rails). Call when the user asks what GTM Vault can do or which playbook or skill fits their problem.
Inputs: no named parameters.
run_layer_auditRevenue system auditARead-onlyInspect
The GTM Vault revenue system audit: eight questions, one per layer of revenue architecture. Called with no answers, it returns the eight questions. Called with all eight answers, it returns the weakest layers, why, the episodes that address them, and a link to the matching stack build.
Inputs: answers.
search_vaultSearch GTM VaultARead-onlyInspect
Search every GTM Vault Podcast, Show Me Your Stack and Coffee Walk episode, write-ups and transcripts. Use when the user asks how operators handled a GTM problem, what a guest said about a topic, or wants evidence for a recommendation. Returns short excerpts with episode links and, for transcript matches, a timestamp link. Each result carries its episode code.
Inputs: query (required), show, limit, content_type.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Search and ask the podcasts you follow inside Claude, with the exact quote and timestamp.
GTM operations knowledge: delivery playbooks, field studies, benchmarks and operator interviews.
Your audit methodology inside Claude: findings, risks, controls and workpapers in your team format.
GA4 conversion analyst inside Claude — funnel drops, traffic anomalies, device gaps, with numbers.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceHosted Claude connector that turns the podcasts you already follow into a searchable, askable knowledge source. Ask what a guest said and get the answer back with the exact quote and timestamp.MIT
- AlicenseNot gradedqualityDmaintenanceEnables B2B prospecting from natural language: detect buying signals, score leads against ICP, enrich decision-makers, and draft personalized outreach messages via Claude.3MIT
- AlicenseBqualityCmaintenanceConnects documentation, GA4 search analytics, Jenkins CI pipeline, and RAGAS-style evaluation to Claude for content gap analysis and documentation improvements.62MIT
- AlicenseNot gradedqualityCmaintenanceEnables B2B prospecting directly inside Claude by sourcing companies from live job postings, enriching them with LinkedIn and Crunchbase firmographic and funding data, and scoring each account 0-100 with an auditable reason for every point. It also surfaces named decision-makers with verified work emails and stores, budgets, and exports the resulting leads locally without ever sending anything.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.