AI & Machine Learning

research-agent.net

Manages research agents for deep-web queries.

1 endpoint26 known toolsFirst detected May 17, 2026Last detected August 27, 2026

ENDPOINT 1

https://research-agent.net/mcp/%7Bapi_key%7D

No auth detected

MCP server metadata

Name: Research Agent
Version: 1.12.4

Capabilities

experimentalpromptsresourcestools

Server instructions

Research Agent lets you run deep-web research queries, create/edit/delete reusable research agents, run them, view past results, and check your credit balance. Each research or agent-run call costs 1 credit. Use enrich_company for quick company lookups, find_buying_signals for GTM signals, and score_icp_fit to qualify leads. enrich_leads_bulk handles batch enrichment. Before choosing a model or writing an output schema for research/create_agent, call list_models — it returns which model fits which task and how to author a prompt + JSON schema the model can reliably satisfy.

Known tools 26

research

Run a deep-web research query (costs 1 credit).

Inferred read-only

list_agents

List all your configured research agents with their IDs, models, and input variables.

Inferred read-only

get_agent

Get full details of a specific agent by ID.

Inferred read-only

create_agent

Create a new research agent.

Potential side effects

create_agent_from_template

Create a new agent from a pre-built template (use list_templates first).

Potential side effects

update_agent

Update an existing agent's configuration.

Potential side effects

delete_agent

Permanently delete an agent.

Potential side effects

run_agent

Execute a configured research agent with input variables (costs 1 credit).

Potential side effects

list_agent_runs

List past runs for an agent with their results.

Inferred read-only

list_templates

List available pre-built agent templates you can create agents from.

Potential side effects

check_credits

Check your current credit balance and recent transactions.

Inferred read-only

get_usage

Get your usage statistics for the last N days.

Inferred read-only

get_me

Get the current user's identity (id, email, display_name, created_at).

Potential side effects

bulk_run_agent

Submit a bulk run job to execute an agent on many inputs at once.

Potential side effects

get_bulk_run_status

Check the progress of a bulk run job.

Inferred read-only

get_bulk_run_results

Get results from a bulk run job (supports pagination).

Inferred read-only

cancel_bulk_run

Cancel a running bulk job.

Inferred read-only

list_bulk_runs

List all bulk run jobs for an agent.

Inferred read-only

search_web

Search the web for a query and return results (costs 1 credit).

Inferred read-only

scrape_page

Scrape and summarize the content of a web page (costs 1 credit).

Inferred read-only

enrich_company

One-shot company enrichment — returns structured company data (costs 1 credit).

Inferred read-only

find_buying_signals

Find recent buying signals for a company — funding, hires, launches, expansions (costs 1 credit).

Inferred read-only

score_icp_fit

Score how well a company fits your Ideal Customer Profile (costs 1 credit).

Inferred read-only

list_models

List available models WITH guidance on which model fits which task and how to set up a prompt + schema correctly.

Inferred read-only

get_plans

List available billing plans and their prices.

Inferred read-only

enrich_leads_bulk

Bulk-enrich a list of companies.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.research-agent]
url = "https://research-agent.net/mcp/%7Bapi_key%7D"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "research-agent": {
      "type": "http",
      "url": "https://research-agent.net/mcp/%7Bapi_key%7D"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: research-agent
Remote MCP URL: https://research-agent.net/mcp/%7Bapi_key%7D

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "research-agent": {
      "url": "https://research-agent.net/mcp/%7Bapi_key%7D"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "research-agent": {
      "type": "http",
      "url": "https://research-agent.net/mcp/%7Bapi_key%7D"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "research-agent",
  "transport": "streamable-http",
  "url": "https://research-agent.net/mcp/%7Bapi_key%7D"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.