Skip to main content
Glama
BlockRunAI

BlockRun MCP

Official
by BlockRunAI
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

blockrun_exa

Read-only

Search the web semantically to get context-aware answers, fetch page contents, and find similar results for research.

Instructions

Neural web search via Exa — understands meaning, not just keywords. Great for research.

Common paths (all POST, body shapes documented in the exa-research skill):

  • search — body: { query, numResults?, category?, includeDomains?, excludeDomains? } ($0.010 base + tx fee)

  • answer — body: { query } ($0.010 base + tx fee)

  • contents — body: { urls: [...] } ($0.002/URL + ONE tx fee, up to 100)

  • find-similar — body: { url, numResults? } ($0.010 base + tx fee) Tx fee = the gateway's flat network fee, $0.001 today (we reserve $0.002); the 402 header carries the exact charge.

Categories for search: "news", "research paper", "company", "tweet", "github", "pdf".

Full request/response shapes + worked research workflows in the exa-research skill.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyNoJSON body for the call. Sent as POST. Required for all four endpoints.
pathYesEndpoint name under /v1/exa/, e.g. 'search', 'answer', 'contents', 'find-similar'
agent_idNoAgent identifier for budget tracking and enforcement.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.45.1
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
  2. First observedv0.16.2

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already cover read-only and non-destructive behavior, so the description appropriately focuses on adding value: pricing, per-URL limits, 402 header handling, and allowed category values. These behavioral details go beyond the annotations but do not exhaustively describe every edge case.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The bulleted list for endpoints and pricing is easy to scan, the essence (semantic search) is front-loaded, and the final pointer to the skill compresses unnecessary detail. Every line carries concrete reference information; there is no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Because the output schema is absent, the description delegates full request/response shapes to the exa-research skill, which is an acceptable pointer given the tool's complexity. It covers request shapes and costs, but an agent expecting a self-contained answer would still need to consult the skill.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description gives the exact body shape for each path, marks optional fields with '?', lists category values, and provides cost figures. This is far richer than the input schema's property descriptions, which only say 'endpoint name' and 'JSON body for the call'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states 'Neural web search via Exa — understands meaning, not just content,' which gives a concrete verb and resource. It enumerates four endpoints (search, answer, contents, find-similar), making it clearly distinct from generic search siblings like blockrun_search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear context: 'Great for research' and emphasizes semantic meaning over keywords. However, it does not explicitly name which sibling tools are alternatives or state when not to use this tool. Still, the context is sufficient for an agent to gauge when to choose it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools