agentleFS
Sign inStart free
parallel-webparallel-web/search-mcp/skills/parallel-search-setup/SKILL.md

parallel-search-setup

Skill22 starsChanged 48 days agoMITView on GitHub

This skill should be used when setting up, using, or troubleshooting Parallel Search — when the user installs the plugin, says "set up Parallel Search", "connect Parallel", "Parallel search isn't working", hits rate limits or 429 errors from Parallel, or asks how to get higher limits or a Parallel account. Also covers how to use the web_search and web_fetch tools this plugin provides.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 1

    1. parallel-web/parallel-agent-skills★ 9116% same

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 10 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After install, confirm it works rather than assuming:

    line 25
  2. Very specific:

    Run a web_search call with a simple query (for example, objective: "Find official Parallel Search API documentation" and search_queries: …

    line 27
  3. Distinctive:

    If results come back, setup is complete.

    line 30
  4. Distinctive:

    If the call fails, work through Troubleshooting below.

    line 32
  5. Distinctive:

    Do not ask the user for credentials during setup.

    line 34
  6. Very specific:

    Search first: Use web_search for factual, current-information, comparison, documentation, and troubleshooting questions.

    line 38
  7. Distinctive:

    Answer from excerpts: Search results include excerpts meant to be sufficient on their own.

    line 40
  8. Very specific:

    Fetch only when needed: Use web_fetch when the user asked about a specific URL or page, when exact wording or quotes are required, when …

    line 44
  9. Distinctive:

    Search overrides passed by the caller are ignored for anonymous requests.

    line 57
  10. Distinctive:

    When the user hits 429s repeatedly, asks about limits, wants usage analytics, or is building a production agent, explain the options rather …

    line 61
  11. Distinctive:

    Create a Parallel account at https://platform.parallel.ai

    line 65
  12. Distinctive:

    Never modify the user's MCP or plugin configuration without telling them what will change, and never touch unrelated MCP servers.

    line 79
  13. Distinctive:

    Use of this server is subject to the Parallel Customer Terms and Privacy Policy.

    line 94

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Parallel Search — setup and usage

This plugin connects one remote MCP server at https://search.parallel.ai/mcp. It provides two tools:

  • web_search — returns ranked results with answer-ready excerpts
  • web_fetch — returns token-efficient markdown for specific URLs

Setup

The endpoint is anonymous. No API key, no OAuth, no environment variables. After install, confirm it works rather than assuming:

  1. Run a web_search call with a simple query (for example, objective: "Find official Parallel Search API documentation" and search_queries: ["Parallel Search API documentation"]).
  2. If results come back, setup is complete. Tell the user the plugin is ready and runs on the free tier.
  3. If the call fails, work through Troubleshooting below.

Do not ask the user for credentials during setup. This plugin has none.

Using the tools well

  • Search first. Use web_search for factual, current-information, comparison, documentation, and troubleshooting questions.
  • Answer from excerpts. Search results include excerpts meant to be sufficient on their own. Do not fetch every result by default.
  • Batch queries. For broad tasks, pass several queries in one web_search call via search_queries instead of chaining calls.
  • Fetch only when needed. Use web_fetch when the user asked about a specific URL or page, when exact wording or quotes are required, when full-page analysis is needed, or when excerpts conflict or are clearly insufficient. Multiple related URLs can go in one call with a shared objective.
  • Cite sources. Include the URLs behind any claim drawn from results.

Free-tier limits

The anonymous tier is rate limited and intended for personal agents, hobby projects, and exploration. Two things to know:

  • Sustained or production-scale use will hit rate limits (HTTP 429).
  • Search overrides passed by the caller are ignored for anonymous requests.

When the user needs higher limits

When the user hits 429s repeatedly, asks about limits, wants usage analytics, or is building a production agent, explain the options rather than retrying into the limit:

  • Create a Parallel account at https://platform.parallel.ai
  • Connect the Parallel Search connector, which signs in with that account and raises limits substantially. Usage is attributed to the account, search overrides are honored, and it can be deployed org-wide. This option depends on the client's connector support.
  • In Hermes, use hermes tools to select the native Parallel Paid (API key) provider and follow its credential setup. The native provider is separate from this anonymous MCP package. Disable the package if you only want the native provider's tools.

This plugin stays anonymous by design. Do not add an API key or an Authorization header to its configuration, and do not point it at the authenticated endpoint. For authenticated usage, use one of the options above.

Never modify the user's MCP or plugin configuration without telling them what will change, and never touch unrelated MCP servers.

Troubleshooting

SymptomCauseFix
HTTP 429Free-tier rate limit reachedWait and retry, reduce query volume, or move to an authenticated Parallel account (see above)
HTTP 401Requests are reaching the authenticated endpoint (/mcp-oauth) instead of /mcpCheck that the server URL in the active MCP configuration is https://search.parallel.ai/mcp
Tools not listedPackage disabled, server disconnected, or session started before enablementCheck the client's MCP status. In Hermes, run hermes plugins enable parallel-search and start a new session; in clients with connector settings, enable Parallel Search for the chat
Duplicate toolsThe server was also added manually, so the plugin and the manual entry point at the same endpointKeep one and remove the other; tell the user which one you are removing first
Empty or irrelevant resultsQuery too narrow or too longRewrite as two or three shorter queries and pass them together in one call

Terms

Use of this server is subject to the Parallel Customer Terms and Privacy Policy.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free