AgentPulse MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| api_key | No | Optional AgentPulse Pro API key appended as a query parameter to the remote MCP URL, e.g. ?api_key=agp_live_... | |
| AGENTPULSE_API_KEY | No | Optional AgentPulse Pro API key used by the local stdio bridge, e.g. agp_live_... |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| enrich_company_domainA | Live B2B company & domain enrichment at the edge. Crawls homepage, /contact, /about, /pricing, and /llms.txt in parallel to extract verified emails (categorized by role), phone numbers, social profile URLs (LinkedIn, X, GitHub, YouTube), 35+ tech stack signatures (CMS, Frameworks, Analytics, Pixels, Payments, CRM), compliance certifications (SOC 2, HIPAA, GDPR), and B2B buying intent signals. |
| audit_ai_search_readinessA | Complete 2026 AI Search & Answer Engine Optimization (AEO / GEO) auditor. Scores any domain from 0-100 on readiness for ChatGPT Search, Perplexity, Claude, and Google AI Overviews. Parses /llms.txt, /llms-full.txt, /robots.txt permissions for 8 AI bots (GPTBot, OAI-SearchBot, ClaudeBot, PerplexityBot, Google-Extended), Schema.org JSON-LD entities, and auto-generates a ready-to-deploy /llms.txt file and Organization JSON-LD snippet. |
| extract_clean_markdownA | Convert any live web URL into clean, token-efficient GitHub-Flavored Markdown with YAML frontmatter (title, description, canonical URL, timestamp, token savings metrics). Strips scripts, navbars, cookie banners, and DOM bloat for optimal LLM context ingestion. |
| inspect_domain_infraA | Inspect live DNS, Email Deliverability (SPF/DMARC/MX), Security Headers (HSTS/CSP), and Verified Enterprise SaaS TXT footprints (OpenAI, Anthropic, Stripe, Slack, Atlassian, HubSpot, Google, Microsoft 365 domain verification tokens) via Cloudflare DNS-over-HTTPS. |
| batch_enrich_domainsA | Bulk parallel B2B enrichment, AEO scoring, or DNS inspection for up to 25 domains in a single request (Requires Growth Pro or Agency Scale API Key). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
The four core tools target clearly distinct resources: B2B enrichment, AEO scoring, markdown conversion, and DNS/infra inspection — an agent should have no trouble picking among them. The one soft boundary is batch_enrich_domains, which explicitly re-runs enrichment, AEO scoring, and DNS inspection in bulk, so the model must decide single vs. batch on top of choosing the operation.
All names are snake_case and four of five follow a verb_noun pattern (enrich_company_domain, audit_ai_search_readiness, extract_clean_markdown, inspect_domain_infra). The outlier is batch_enrich_domains, which leads with a modifier and uses a different object form than enrich_company_domain, a minor but noticeable deviation.
Five tools is well within a healthy range and each maps to a distinct capability (single enrichment, bulk enrichment, AEO audit, infra inspection, content extraction). There is no filler tool and no obvious fragmentation that should have been consolidated.
The surface covers the main domain-intelligence workflows end to end, including a bulk path for scale. Gaps are minor: extract_clean_markdown has no batch counterpart, bulk mode is gated behind a paid key with no async/job-status or result-retrieval tool, and there is no way to revisit prior enrichment results.