NeuralVerge MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HTTP_PATH | No | HTTP path for the MCP endpoint. Defaults to /mcp. | /mcp |
| MCP_HTTP_PORT | No | Port for http transport. Defaults to 8787. | 8787 |
| MCP_TRANSPORT | No | Transport mode: 'stdio' (default) or 'http'. | stdio |
| MCP_HTTP_AUTH_TOKEN | No | If set, http transport requires Authorization: Bearer <token> on every request. | |
| NEURALVERGE_API_KEY | Yes | Your NeuralVerge API bearer token (required). | |
| NEURALVERGE_BASE_URL | No | Override the NeuralVerge API base URL. Defaults to https://api.neuralverge.ai. | https://api.neuralverge.ai |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| run_researchA | Starts the full NeuralVerge AI research workflow (multi-step search, analysis, and structured reporting) and returns a session_id immediately. Poll get_session_status with that session_id until status is 'complete' or 'failed'. |
| run_agentA | Runs a saved NeuralVerge agent (a reusable, preconfigured workflow) by its agentId and returns a session_id immediately. Poll get_session_status with that session_id until status is 'complete' or 'failed'. |
| get_session_statusA | Returns the current status of an AI Research or AI Agent session (queued/running/complete/failed) and the final result (human-readable summary plus machine-readable JSON) once processing completes. |
| run_searchA | Runs a synchronous web search and returns a structured list of ranked results (title, url, snippet) immediately, without polling. |
| run_extractA | Loads a webpage by URL and extracts structured data from it according to natural-language instructions and/or a JSON schema. Synchronous — returns the result immediately. |
| run_linkedin_emailA | Looks up a LinkedIn profile by its full profile URL and returns contact details, including an email address when available. |
| run_linkedin_domainA | Finds a LinkedIn profile matching a company name or domain plus a full name. |
| run_linkedin_company_searchA | Searches LinkedIn companies by a text query with optional filters (size, industry, location). |
| run_linkedin_people_searchA | Searches LinkedIn people using an optional free-text query and a rich set of advanced filters (company, title, seniority, location, experience, industry). |
| run_linkedin_company_employeeA | Searches LinkedIn employees of one or more given companies, using the same people-style filters as run_linkedin_people_search. |
| run_email_enrichmentA | Enriches a known email address with associated profile data (name, phone, company, position, LinkedIn/X profiles) when available. |
| run_email_validationA | Validates an email address and returns deliverability signals (valid/invalid/risky, catch-all detection, provider, confidence). |
| run_email_finderB | Finds a professional email address for a person given their company domain, first name, and last name. |
| run_phone_enrichmentB | Enriches a known phone number with associated profile data (name, email, company, LinkedIn/X profiles, carrier) when available. |
| run_phone_enrichment_usA | Validates and enriches a US phone number with carrier, line type, activity score, litigator risk, and owner details. |
| run_crunchbase_companyA | Fetches structured company data (website, location, founding year, employees, industries, funding, description) from a Crunchbase company URL. |
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 16 tools
Multiple tools target similar actions (email finder vs LinkedIn email, people vs company employee search, phone vs US phone enrichment), and async workflows (research vs agent) are easy to confuse. Descriptions help clarify, but boundaries between tools are not always sharp.
Strong run_ prefix creates a consistent feel, but suffixes mix verb-style (search, extract) and noun-style (email_finder, phone_enrichment_us) naming. The outlier get_session_status breaks the run_ pattern, and run_linkedin_domain is misleading (it does not search by domain).
With 16 tools, this is slightly above the typical 3-15 range, but the server covers distinct domains (research, search, LinkedIn, email, phone, Crunchbase), so each tool earns a place. The count feels justified for a comprehensive enrichment platform, though it borders on heavy.
Core data retrieval surfaces are well covered: research workflow, search, extraction, LinkedIn, email, phone, and company data. Notable gaps include no agent management (list/create agents) and no session control (cancel/pause), but most practical workflows are supported.