Skip to main content
The Keenable Model Context Protocol (MCP) server gives your agent web search and page fetch as tools. It works in Claude Code, Claude Desktop, Cursor, Devin Desktop (formerly Windsurf) and other MCP clients. If you don’t send an API key, the server answers on the shared public tier. Send your key in the X-API-Key header to remove the hourly request limit, raise rate limits and add the Monitors tools. See Authentication and Rate limits. If your agent has no MCP client, the agent skill gives it search through a bundled script instead.

Which URL to use

Use https://api.keenable.ai/mcp unless your client signs in through a browser. It works with no key or with an X-API-Key header, which covers Claude Code, Cursor, Codex with a key and most config files. Use https://api.keenable.ai/mcp-oauth only for a client that signs in, such as a custom connector in Claude: it asks every caller that sends no credential to sign in to Keenable, so the client opens the sign-in page. All three URLs serve the same two web tools. With an API key or after you sign in, the server also lists the Monitors tools. For every way an agent can authenticate, including REST and pay per request, see Access methods for agents.

Installation

Keenable is also listed in MCP registries and directories, such as the official MCP Registry and the GitHub MCP Registry. See MCP registries and directories.

One-click install

Add Keenable to Cursor, VS Code or Replit with one click:

Install via CLI

For local coding agents, the Keenable CLI sets up the MCP server for you. Once you’ve installed the CLI, run this command and confirm the change:
The CLI adds Keenable to every client it detects among Claude Code, Cursor, Devin Desktop (including the legacy Windsurf path), Codex and OpenCode. See MCP setup for the flags and the files it edits.

Claude Code

Add the Keenable MCP server with the Claude Code CLI:
Omit the --header flag to run on the public tier instead. Claude Code ships its own WebSearch and WebFetch tools and picks between them and Keenable from one lookup to the next. To leave Keenable as the only search, add "permissions": { "deny": ["WebSearch", "WebFetch"] } to ~/.claude/settings.json. See Claude for the details and how to undo it.

Codex

Add the server to ~/.codex/config.toml:
To run on the public tier instead, omit the http_headers line and change the URL to https://api.keenable.ai/mcp-public. /mcp publishes OAuth discovery metadata, which can make Codex start a browser sign-in when it has no key. See Keyless endpoint for listings and presets.
Codex ships its own web search, turned on by default, and keeps using it instead of Keenable. The Keenable tools show up in /mcp, but Codex calls them only when you ask for them by name. To fix this, add web_search = "disabled" to the same file, above the [mcp_servers.keenable] line. It’s a top-level key: if you write it under a table header, it belongs to that table and Codex never reads it. See Codex for the finished file, the other modes and an AGENTS.md snippet.

Other MCP clients

Most other clients connect to the same remote URL. Each one has its own config path and its own name for the URL key: Most clients take this shape. Replace url with serverUrl or httpUrl if the table lists that key:
Omit the headers block to run on the public tier instead. If a client fails on OAuth discovery, as Antigravity and some marketplace presets do, use https://api.keenable.ai/mcp-public instead. See Keyless endpoint for listings and presets. If your client has its own web tools, such as WebSearch, WebFetch, brave_search or tavily_search, turn them off in the client settings. With both sets active, the agent picks between them inconsistently from one call to the next. See Make Keenable the default web tool for the setting in each client. To have a coding agent check a library’s current docs before it writes code, add the rule in Docs lookup for coding agents.
Claude Desktop’s config file accepts only local command servers. If you add a "url" entry, Claude Desktop ignores it without an error and the tools never appear. Use a connector instead, or the local bridge if you want your key applied.

Keyless endpoint for listings and presets

If you ship Keenable to your users with no key, for example in a preset, a catalog entry or a docs example, use this URL:
It is the same server with the same two tools. On /mcp-public, the search_web_pages schema doesn’t list the mode parameter. Keyless calls get the same public tier: 1,000 requests per hour and up to 10 per second per IP address (see Rate limits). The difference is that /mcp-public publishes no OAuth discovery metadata. Clients that read discovery before anything else, such as Google Antigravity, connect right away instead of offering a sign-in. An X-API-Key header works on /mcp-public the same way as on /mcp and lifts the hourly limit. If the server doesn’t accept the key, it returns 403, not 401, so the client shows the error instead of offering a sign-in. Use /mcp for setups where users add their own key, and /mcp-oauth for setups where they sign in.

OpenAI API (Responses API)

Use this to call the MCP server from your own code through OpenAI’s Responses API. To add Keenable inside the ChatGPT app, use the Plugins Directory listing instead. Pass the server as a remote mcp tool:
The script prints the model’s answer. Omit the headers entry to run on the public tier instead.

Claude (remote connector)

Claude (Desktop, claude.ai, mobile) connects to the remote MCP server as a connector, with no config file.
1

Add the connector

Keenable is listed in Claude’s Connectors Directory as Keenable Web Search: open Customize → Connectors, click +, search for it, and click Connect. There is nothing to paste.To run on your own Keenable account, add it by URL instead: Customize → Connectors → + Add → Add custom connector with the URL below, then click Connect and sign in to Keenable. An API key in a request header works too; see Claude.
2

Enable it in a chat

Click + in the lower left of the message box, hover Connectors, and toggle Keenable on for the conversation.
To stop Claude’s own web search from competing with Keenable, see Claude.

Local bridge (with an API key)

If a client supports only local stdio servers, it needs a bridge to send your key. Claude Desktop’s config file is the common case. The bridge needs Node.js 18 or newer. The @keenable/mcp package runs as a subprocess and forwards requests to the same endpoint:
Restart the client after you edit its config file (for Claude Desktop, claude_desktop_config.json). Drop the env block to run the bridge without a key. The same block works in the config of any other stdio-only client. The bridge connects to https://api.keenable.ai/mcp when your client starts it, and waits up to 10 seconds for an answer. If it can’t connect, for example while you’re offline or when Keenable rejects your API key, it starts anyway and the tools still appear. A tool call then returns an error that starts with Keenable request failed: and gives the reason, such as Malformed API key or fetch failed (ECONNREFUSED), so your agent can tell you what went wrong. Fix the network connection, the proxy or the key in the env block. You don’t need to restart the client: every tool call tries to connect again. The client’s MCP log shows the same reason in a line that starts with keenable-mcp: could not connect to https://api.keenable.ai:. A session that started without a connection doesn’t get the server’s instructions for the agent. They come back the next time your client starts the bridge. Node.js doesn’t use the HTTPS_PROXY variable unless you tell it to. If you connect through a proxy on Node.js 22.21 or newer, add "NODE_USE_ENV_PROXY": "1" to the env block next to your proxy variables.

Available tools

The MCP server has two web tools, search_web_pages and fetch_page_content, on every URL. With an API key or after you sign in, it also has the Monitors tools. To have a coding agent check library docs with them before it writes code, see Docs lookup for coding agents.

search_web_pages

Search the web and return ranked results with URLs, titles, and snippets.
string
required
The search query.
string
Return results from one site only, such as "techcrunch.com".
string
What this search is for, in two or three plain sentences with no field labels. Say which facts a useful page must contain, what the query leaves out (who, where, when, the date window), which kinds of sources count or must be excluded, what you already know and what is still unknown. Don’t paste the conversation, and leave out personal or confidential information. At most 1,000 characters. Keenable validates and logs it. It doesn’t change the results or the price yet.
array of strings
Never return results from these hosts, such as ["pinterest.com", "quora.com"]. Each host also covers its subdomains. Up to 1,000 entries. A public suffix written with a leading dot, such as .gov, excludes every host under it. No paths or wildcards on a host. A scheme, a leading www. or a trailing / is cleaned up. A single host name as a string also works. A rejected entry returns a tool error that names the entry and the reason. See Exclude domains.
string
Keep only pages Keenable acquired (indexed) at or after this point. See Date and time filters for the formats.
string
Keep only pages Keenable acquired (indexed) at or before this point. See Date and time filters for the formats.
string
Keep only pages published at or after this point. See Date and time filters for the formats.
string
Keep only pages published at or before this point. See Date and time filters for the formats.
string
Search the index as it stood at this point in time: pages acquired after it are excluded. Accepts a timestamp, a date (a date resolves to 00:00:00 UTC, not to the end of the day), a Unix epoch, or a relative delta such as 7d, which means the index as it stood 7 days ago. See Point-in-time search.
integer
Maximum length, in characters, of the snippet returned per result. Must be between 180 and 10000. When omitted, a default snippet length is used.
integer
Maximum number of results to return. Must be between 1 and 50. When omitted, up to 10 results are returned.
string
Search mode: pro for higher-quality results or realtime for the fastest results. When omitted, the search runs in pro mode.
string
default:"text"
text for readable text, or json for the raw response serialized as JSON, for when your code parses the fields.
string
ID of the agent session making the call, up to 128 characters. Send the same value on every call in one session so its requests can be grouped.
boolean
default:"false"
Set to true to leave cards out of the results. A card is a result that Keenable writes itself for queries such as prices, exchange rates or facts about a company, at a URL such as https://cards.keenable.ai/w/<id>. A card URL works for one day. With disable_cards, ordinary web pages take the place of cards, so you get the same number of results.

Date and time filters

acquired_after, acquired_before, published_after and published_before each take one of these formats:
  • A date in RFC 3339 full-date form (YYYY-MM-DD). It covers that whole day in UTC. On an _after bound it resolves to 00:00:00 on that date. On a _before bound it resolves to 23:59:59.999 on that date, so pages from the named day are kept at either end. Pass a timestamp instead to cut at an exact instant.
  • A timestamp in ISO 8601 form (YYYY-MM-DDTHH:MM:SS[.sss][±HH:MM]). If the timestamp has no timezone offset, the server reads it as UTC.
  • A relative delta (<number><unit>, such as 7d or 30min). It resolves to the request time minus the delta, truncated to the minute, even if query_time is set. The units are min (minutes), h (hours), d (days), w (weeks), mo (30 days) and y (365 days).
These values resolve as follows: You can use a relative delta on either bound of a window, together with another delta or an absolute value on the other bound. This window keeps pages published between one year and six months ago:
This one keeps pages acquired from 1 January 2024 up to 30 days ago:
For example, at request time 2026-05-18T14:23:45Z, acquired_after: "2h" resolves to 2026-05-18T12:23:00Z. A page acquired at 12:22:59Z is dropped, and a page acquired at 12:23:00Z is kept. On a _before bound, a date and a timestamp cut at different points: acquired_before: "2026-05-01" keeps a page acquired at 2026-05-01T14:31:13Z, while acquired_before: "2026-05-01T00:00:00Z" drops it. Use the date form to mean “up to and including that day”, and the timestamp form to cut at midnight. query_time runs the search against the index as it stood at an instant. A page acquired after that instant isn’t a candidate, so you get the results the index would have returned then, not today’s results filtered down. Use it to reproduce an agent run, to build an evaluation set that doesn’t drift as the index grows, or to ask what was knowable before an event. Relative deltas in the other filters still count back from the request time, not from query_time. To bound results around a past instant, use dates. This request returns pages published in the 30 days before 13 June 2026, as the index stood then:
A date-only query_time resolves to 00:00:00 UTC, which is the opposite end of the day from a date-only _before bound: query_time: "2026-06-13" cuts at the start of 13 June, while acquired_before: "2026-06-13" keeps all of it.

fetch_page_content

Fetch a URL and get its content as clean markdown. By default, the tool fetches only URLs in the Keenable index. Pass live=true to fetch directly from the source, including URLs that aren’t indexed.
string
required
The URL to fetch.
integer
default:"20000"
Maximum number of characters of content to return. Longer content is truncated. The MCP default is lower than the API’s 50,000, so a long page fits in an agent’s context; for one detail from a long page, use prompt instead.
boolean
default:"false"
Fetch the page live from the source instead of returning Keenable’s indexed copy. Enables fetching URLs that are not indexed.
string
An instruction for what to pull from the page, at most 2,000 characters. If you set it, an LLM reads the fetched page and the tool returns only its answer, not the full page. Example: List all pricing tiers with their monthly prices.
string
default:"text"
text for readable text, or json for the raw response serialized as JSON, for when your code parses the fields.
string
ID of the agent session making the call, up to 128 characters. Send the same value on every call in one session so its requests can be grouped.
In text format, the tool returns the page title, the URL and the content as markdown. If the content is cut at max_chars, a Truncated: line gives the full length. In json format, it returns the response described in the Fetch reference.

Monitors tools

With these tools, your agent can create monitors, which watch the web for new pages about a topic, and read their results. The server lists the tools only if the connection carries an API key or a Keenable sign-in. The tools act on the monitors of your organization, the same ones the Monitors API shows, under the same limits. The server lists four Monitors tools, in this order: The tools take their own argument names, in camelCase, not the HTTP API’s fields. To pause, resume, rename or change a monitor, start a run outside its schedule, or read a run, use the Monitors API, an SDK or the CLI. If a prompt or scheduled task still names whats_new or monitor_pages, see Four Monitors tools over MCP for the new names. For full builds, see the News monitor to Slack and Competitor watch recipes. get_monitor_results keeps track of what each reader was given on Keenable’s side, not in the chat. A new chat continues where the last one stopped. The first call for a monitor returns its results from the last 24 hours. Each result has url, title, summary, importance (1 to 5), publishedDate and the monitor it belongs to. peek: true returns the results without marking them as read. If several people or scheduled tasks in one organization should each get every result, give each a different reader name of up to 40 characters. Without reader, they share one reader and split the results between them. If the response has hasMore: true, more results are waiting: call the tool again. An empty response means nothing new arrived. To look back over results already read, pass includeSeen: true with a monitorId. You get that monitor’s last 500 results, newest first, a page at a time. Pass the response’s nextCursor as cursor to get the next page. includeSeen without monitorId returns the error includeSeen needs monitorId, and cursor without includeSeen returns cursor needs includeSeen. The MCP server can’t start a conversation, so your agent learns about new results only when it calls get_monitor_results. To be told about them, give the agent a scheduled task, in Claude or ChatGPT, with a prompt like this:
To have each new result pushed to your server instead, pass webhookUrl to create_monitor: a public HTTPS address. The monitor sends each new result to it as soon as it is found, without waiting for get_monitor_results. The response has the signing secret once, as webhookSecret. Store it then: no later response shows it. The secret also sits in the chat transcript, so treat it like any key you paste into a chat. Without webhookUrl, the response has no webhookSecret. Deliveries are signed under the Standard Webhooks scheme, so verify each one as Monitors describes, with the secret in place of webhook.secret. A secret looks like whsec_example. To change or add a webhook later, use the Monitors API. See Monitors for the events.

Search these docs over MCP

These docs are a separate MCP server at https://docs.keenable.ai/mcp, so your coding agent can look up Keenable parameters and errors while it writes code. It needs no key. Add it to Claude Code:
Other clients take the same URL as a remote server. The docs server lists these tools:

Server info

The initialize response describes the server for client UIs and MCP directories. Besides name and version, serverInfo carries:

Metadata for integrators

If your platform embeds Keenable’s MCP tools, you can read billing usage and control tool behaviour through the MCP _meta field. _meta travels next to the tool result or request, outside the content the model sees, so none of it enters the agent’s context. Baseten uses both channels to run the tools as hosted tools on its Model APIs.

Usage metadata (response _meta)

Every billed (authenticated) tool call returns usage under _meta["keenable/usage"], so you can attribute cost per call without parsing the tool’s text output. If a call has no API key, it isn’t billed and the result has no keenable/usage.
string
Billing SKU for the operation: search.realtime, search.pro, fetch, or fetch.live.
integer
Number of billed operations. Always 1 for a single tool call.
number
What this call cost, in credits, at your organization’s price. One credit is $0.004.
boolean
true when drawn from your prepaid balance; false while still on the free monthly allowance. See Balance and usage.
number
Credits your organization has left after the call: the unused part of the free allowance for the current billing period plus your prepaid balance, in credits of $0.004. An estimate that can lag your other calls by a few seconds. Left out if the balance couldn’t be read.
A billed tool result looks like this:

Operator overrides (request _meta)

To control tool behaviour yourself instead of letting the model decide, send overrides under _meta["keenable/overrides"] on a tools/call request. They take precedence over the arguments the model generated.
string
Force the search mode: realtime or pro. Overrides any mode the model chose.
boolean
Bypass cached results for this call.
This request forces realtime mode and skips the cache:
If an override value is invalid or unknown, the server ignores it and runs the call.

Tool calling

Give an LLM web search and page fetch as tools. Pass the SDK’s TOOLS to any OpenAI-compatible chat completions client and run each call with run_tool_call.

Integrations

Connect Keenable web search to your agent stack: LangChain, LlamaIndex, Haystack, MCP and more.

Choose a product

Pick Search, Fetch, SELECT, Monitors or pay per request by the job your agent has to do: what each returns, the access it needs and its price.

Production checklist

Ship Keenable search and fetch to production: keys from the environment, rate limits, retries on 429 with Retry-After, stopping on 402, timeouts and status.