Context.dev MCP

Live

OAUTH 2.1

WEB DATA

Search

Context.dev MCP gives your agent web data: search, scrape, crawl, and map sites, retrieve brand intelligence, search company news, enrich people, parse documents, and run change monitors.

  • Per-user credentials: each call uses the actual user's token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Context.dev MCP
agent · Acme Q3
Run
Pull the logo, colors, and description for stripe.com.
S
contextdevmcp_brand_retrieve_unified
131ms
Research agent
Found the Stripe brand profile: logo, 3 brand colors, a company description, industry, location, and 5 social links.
Sources: stripe.com, 1 brand profile
contextdevmcp
1 brand
18:29
Message Claude...

Tools your web research agent reaches for on Context.dev, scoped per user.

CALL ANY TOOL
40 tools for web data: search and scrape the live web, crawl and map sites, pull brand and people profiles, run scraping batches, and monitor pages for changes.
contextdevmcp_brand_retrieve_unified
Brand retrieve unified
Retrieve machine-readable company and brand intelligence-logos, colors, descriptions, socials, links, industry, location, and more-from one domain, company name, work email, stock ticker, ISIN, transaction descriptor, or direct URL. Use get-brand for a visual card from a domain; use this tool for raw structured data or non-domain lookups.
Parameters
Name
Type
Required
Description
body
string
Required
Brand lookup request. Provide exactly one lookup type: domain, company name, email, stock ticker, direct URL, or transaction descriptor.
contextdevmcp_brand_search
Search brand
contextdevmcp_cancel_batch
Batch cancel
contextdevmcp_create_monitor
Create monitor
contextdevmcp_delete_batch
Batch delete
contextdevmcp_delete_monitor
Delete monitor
contextdevmcp_get_batch
Batch get
contextdevmcp_get_batch_results
Get batch results
contextdevmcp_get_brand
Get brand
contextdevmcp_get_change
Get change
contextdevmcp_get_monitor
Get monitor
contextdevmcp_get_monitor_limits
Get monitor limits
contextdevmcp_get_monitor_run
Run get monitor
contextdevmcp_get_news_search
Search get news
contextdevmcp_list_account_runs
List account runs
contextdevmcp_list_batches
List batches
contextdevmcp_list_changes
List changes
contextdevmcp_list_monitor_changes
List monitor changes
contextdevmcp_list_monitor_credit_usage
List monitor credit usage
contextdevmcp_list_monitors
List monitors
contextdevmcp_list_webhook_deliveries
List webhook deliveries
contextdevmcp_parse_document
Parse document
contextdevmcp_retry_webhook_delivery
Retry webhook delivery
contextdevmcp_run_monitor_now
Run monitor now
contextdevmcp_submit_batch
Batch submit
contextdevmcp_submit_feedback
Submit feedback
contextdevmcp_update_monitor
Update monitor
contextdevmcp_web_crawl
Web crawl
contextdevmcp_web_scrape
Web scrape
contextdevmcp_web_search
Search web

For more tools, view docs.

Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Context.dev MCP tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["contextdevmcp"], toolNames: [
    "contextdevmcp_web_search",
    "contextdevmcp_brand_retrieve_unified",
    "contextdevmcp_get_news_search"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Pull the logo, colors, and description for stripe.com" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["contextdevmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Pull the logo, colors, and description for stripe.com" }],
  tools,
});

// Execute the tool call with the user's vaulted Context.dev token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["contextdevmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Pull the logo, colors, and description for stripe.com" }],
  tools,
});

// Tool call runs with the user's vaulted Context.dev token
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["contextdevmcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "research_agent",
  model: "gemini-2.5-pro",
  instruction: "Context.dev MCP tools scoped to this user",
  tools,
});

await agent.run("Pull the logo, colors, and description for stripe.com");
Try these prompts
Copy any prompt into your agent. Each maps directly to a Context.dev MCP tool. Click to copy, paste into your agent, done.
Web research
Copy the prompt
Copied
Search the web for recent pricing changes at Acme and scrape the top results.
Copy the prompt
Copied
Crawl the docs section of example.com and return it as Markdown.
Copy the prompt
Copied
Map every URL under example.com/blog.
Brands and people
Copy the prompt
Copied
Get the brand profile for stripe.com.
Copy the prompt
Copied
Extract the style guide from linear.app.
Copy the prompt
Copied
Search news about Acme from the last 2 weeks.
Monitors and batches
Copy the prompt
Copied
Create a monitor that checks our competitor's pricing page daily.
Copy the prompt
Copied
List changes detected by my monitors this week.
Copy the prompt
Copied
Show the status of my latest scraping batch.
SEE HOW AUTH WORKS
Each user signs in to Context.dev once; Scalekit stores and refreshes their tokens. Every call is scope checked, and every action is logged.
1
Authorize
Your user connects
Context.dev MCP
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Context.dev MCP
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Context.dev MCP
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Context.dev MCP
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other web data and search connectors.
GTM and RevOps Teams
Competitive intelligence briefing agent
Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.
GTM and RevOps Teams
Outbound prospecting agent
Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.
Support and Ops Teams
Meeting prep
Pulls agenda, participant context, and open action items before every meeting.
GTM and RevOps Teams
Deal intelligence agent
Pulls recent Gong calls, scores deal risk with an LLM, cross-references the record in Attio, and DMs each owner their at-risk deals in Slack. Every read is scoped to that rep's own access.
Test other agents
See the same per-user auth pattern across other web data and search connectors.
GTM
Competitive intelligence briefing agent
Scan Gong calls for competitor mentions, match each one to its Notion battlecard, and DM every affected rep a single Slack digest.
SALES
Outbound prospecting agent
Search Apollo for ICP matches, rank them, draft personalised Gmail outreach, and log every send to Google Sheets.
OPS
Meeting prep agent
Assemble the agenda, HubSpot attendee history, and open action items from Gmail before every meeting on the calendar.
SALES
Deal intelligence agent
Score Gong call risk with an LLM, cross-reference the Attio record, and DM each owner their at-risk deals in Slack.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared Context.dev token looks fine in a demo. In production every web request looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Context.dev today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does the agent access Context.dev as the user or as a shared key?
As the user. Each user signs in to Context.dev once, and Scalekit stores and refreshes their tokens. Audit logs attribute every action to that user, not a shared service account.
Where is the Context.dev OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.
Can I limit what the agent does in Context.dev?
Yes. Filter by tool name in listScopedTools to expose only what you want. Scalekit also enforces scope checks before every API call.
What happens when a user revokes Context.dev access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.
Which Context.dev tools change state?
12 of the 40 tools write or are marked destructive: creating, updating, running, and deleting monitors, rotating a monitor webhook secret, submitting, cancelling, and deleting batches, retrying webhook deliveries, parsing documents, submitting feedback, and scraping a URL. Leave them out of listScopedTools to keep an agent on read-only research.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""contextdevmcp"": {
""url"": ""https://mcp.scalekit.com/contextdevmcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.contextdevmcp]
url = ""https://mcp.scalekit.com/contextdevmcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""contextdevmcp"": {
""url"": ""https://mcp.scalekit.com/contextdevmcp"",
""type"": ""http""
}
}
}