by Parallel
Updated October 20, 2026
MCP100 verdict
Not currently recommended. First-party evidence supports Shortlist admission; this is not a Recommended-tier security certification.
MCP100 Assessment
Editorial verdict
Reviewed October 19, 2026
Task Fit
Mapped
Web search and research
Trust
Status warning
Shortlist evidence is sufficient for identity, setup and task value; authenticated runtime tool-schema measurement and exhaustive security certification remain out of scope.
Maintenance
Date unavailable
No dated repository or package update is currently stored.
Popularity
Signals unavailable
No independently comparable adoption metric is currently stored.
Evidence scope
26 shared-repository stars · not MCP-specific
No MCP-specific package metric is stored
Repository identity: parallel-web/search-mcp
Stars observed October 20, 2026 · Downloads observed October 20, 2026
Official GitHub home for Parallel's hosted Search MCP. Parallel states the repository contains documentation and client/plugin configuration while the search service runs on Parallel infrastructure, so stars are distribution/configuration evidence rather than hosted-server implementation adoption.
Hosted Parallel Search MCP has no exact public package distribution verified.
Publisher activity observed October 20, 2026
Current source snapshot
Source relationship: First-party MCP
Reviewed October 19, 2026
Evidence-backed setup
Choose your MCP client. A client connects to the MCP server; the language model is selected inside that client. Only stored, source-backed configurations are shown.
Transport not recorded
Complete client-specific setup, verification and removal are not documented in this reviewed source.
Publisher-documented setup is not the same as MCP100 execution testing. “MCP100 logic checked” means the stored configuration shape was reviewed, not that third-party MCP software was run.
Evidence checked 2026-10-20
Type-appropriate, source-backed setup for this mcp server profile.
{"url":"https://search.parallel.ai/mcp"}Capability
Parallel Search MCP is a first-party MCP for give agents current web search and page fetching with a minimal two-tool interface. Authentication/setup: No key required for basic use; Bearer API key optional for higher limits. Open-web content is untrusted and can contain prompt injection. Anonymous use has lower limits; production use can add a Parallel API key.
Parallel documents exactly two default tools for Search MCP: web_search and web_fetch.
Not measured yet
Estimated token footprint of the MCP tool schemas exposed to the agent.
https://search.parallel.ai/mcp
Reviewed access
Related reviewed MCPs
Search Hugging Face Hub resources and use explicitly enabled Jobs, sandboxes, and community Space tools.
Choose this instead if
Choose Hugging Face MCP instead if searching models, datasets, Spaces, papers, and Hugging Face documentation.
Search Hugging Face Hub resources and use explicitly enabled Jobs, sandboxes, and community Space tools.
Search, scrape, crawl, and extract web content through Firecrawl.
Choose this instead if
Choose Firecrawl MCP instead if scraping and extracting public web pages.
Search, scrape, crawl, and extract web content through Firecrawl.
Connect compatible AI clients to Perplexity's documented MCP capabilities.
Choose this instead if
Choose Perplexity MCP instead if current web search and cited question answering with Perplexity APIs.
Recommended first-party Perplexity MCP for real-time search, question answering, reasoning, and deep research through a small four-tool surface.
Parallel is listed as First-party MCP in MCP100’s current evidence.
Current official resources:
Original product, capability, tool, and usage documentation from the MCP publisher. Installation sections appear under Install & Agents.
Free web search for your coding agent.
Find current documentation, check facts, and read web pages without leaving your agent. No account or API key needed to get started.
Copy this into your coding agent:
Install Parallel's free Search MCP in the coding agent I'm using now.
Identify your client and use its native MCP setup instructions:
https://docs.parallel.ai/integrations/mcp/search-mcp
Server name: parallel-search
Server URL: https://search.parallel.ai/mcp
Transport: Streamable HTTP
Authentication: none. No account, API key, or Parallel CLI is needed.
Preserve existing settings and reuse any connection to this endpoint.
Tell me if a restart or approval is required.
Once connected, check that web_search and web_fetch are available.
Use Parallel to find the official FastAPI response-model documentation
and return a source link. Report anything you couldn't verify.
Install in Cursor · Install in VS Code · Manual setup · Documentation
Choose your client. You only need one of these options.
codex mcp add parallel-search --url https://search.parallel.ai/mcp
Start a new Codex session and run /mcp to check the connection. See the Codex MCP guide for configuration options.
gemini extensions install https://github.com/parallel-web/search-mcp
Restart Gemini CLI and run /mcp to check that parallel-search is connected. The extension uses Streamable HTTP and requires no Parallel account or API key. If you already configured parallel-search manually, that configuration takes precedence over the extension. See the extension guide for installation and update options.
Hermes already includes Parallel in its native web providers. Choose Parallel Free (keyless) in hermes tools to use that integration.
This optional package adds a direct connection to Parallel's MCP tools and the bundled setup skill. It leaves Hermes's native web-provider selection unchanged. It's available in the Hermes plugin catalog. Install and enable it with:
hermes plugins install parallel-search
hermes plugins enable parallel-search
Start a new session so Hermes loads the enabled package. Ask Hermes to use the Parallel MCP web_search tool to find official documentation, then web_fetch to read a page. Use skills_list to discover the namespaced parallel-search-setup skill. No Parallel account, API key, or CLI is required.
Use either this package or a manually configured connection to https://search.parallel.ai/mcp to avoid duplicate MCP tools. Disable or remove the package with hermes plugins disable parallel-search or hermes plugins remove parallel-search. Update through hermes plugins update parallel-search; catalog updates use reviewed commit pins.
Merge this into your project's opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"parallel-search": {
"type": "remote",
"url": "https://search.parallel.ai/mcp",
"oauth": false
}
}
}
Restart OpenCode and run opencode mcp list to check the connection. See the OpenCode MCP guide for details.
Follow the OpenClaw setup guide to install the Parallel plugin, then set tools.web.search.provider to parallel-free. No Parallel account or API key is needed.
Use this remote MCP server URL:
https://search.parallel.ai/mcp
Select HTTP or Streamable HTTP if your client asks for a transport. Follow the client-specific instructions for the right settings file and format.
Ask your agent:
Use Parallel to find the official FastAPI docs for response models. Show me a small example and link to the source.
Or try:
Use Parallel to check the latest stable Node.js release and its release notes. Cite the official sources.
Use Parallel to read https://modelcontextprotocol.io/introduction and explain how MCP connects an agent to tools.
Your agent can use two tools:
| Tool | What it does |
|---|---|
web_search | Searches the web and returns relevant excerpts with source links. |
web_fetch | Reads specific URLs and returns page content for your agent to use. |
Search results often contain enough information to answer. Your agent can fetch a page when it needs more detail.
This plugin is anonymous by design: both tools work with no account, API key, or login, subject to free-tier rate limits. The free tier is intended for personal agents, hobby projects, and exploration.
For higher limits, usage analytics, and production workloads, create an account at platform.parallel.ai and connect the Parallel Search connector, which signs in with that account. Authenticated usage is billed under your account's pricing and limits — see parallel.ai for pricing. Don't add an API key or point this plugin at an authenticated endpoint; the connector handles sign-in natively.
Both tiers include the same two tools. Authenticated connections also let you configure search behavior, including search modes, result counts, and domain filters. Anonymous requests ignore these settings.
Parallel hosts the service. Search queries and requested URLs are sent to Parallel and handled under the Customer Terms and Privacy Policy. The server only receives what the tools send it — search queries and the URLs you ask it to fetch — and does not read your conversation, files, or other context.
https://search.parallel.ai/mcp./mcp supports free access; /mcp-oauth requires authentication. Approving an MCP connection in your client is separate from logging in to Parallel.This is the official GitHub home for Parallel's hosted Search MCP. It contains this guide and Codex, Cursor, Gemini CLI, and Hermes packages. Codex and Cursor share .mcp.json; Hermes uses the portable Agent Plugins v1 plugin.json and mcp.json files and loads the setup skill (skills/parallel-search-setup/SKILL.md) on demand for connection checks, usage guidance, troubleshooting, and higher-limit options. You can suggest documentation fixes and examples here. The search service runs on Parallel's infrastructure; cloning this repo gives you the documentation and configuration files.
For CLI-based search, research, and enrichment, see the separate Parallel CLI skills plugin.
The files in this repo are MIT licensed. Hosted service usage is covered by the Customer Terms linked above.