Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.daedalus/mcp-exa

PYPI · MCP-EXA · SCANNED SEP 20

MCP server exposing Exa websearch API

Available components

−15 this week 66 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security49
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 4 of 34 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability68
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1012 tokens (~112/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the io.github.daedalus/mcp-exa server?

io.github.daedalus/mcp-exa runs locally as a PyPI package, launched with uvx mcp-exa. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · mcp-exa

# add to Claude Code
claude mcp add daedalus-mcp-exa -- uvx mcp-exa
// .cursor/mcp.json
{
  "mcpServers": {
    "daedalus-mcp-exa": {
      "command": "uvx",
      "args": [
        "mcp-exa"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "daedalus-mcp-exa": {
      "command": "uvx",
      "args": [
        "mcp-exa"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add daedalus-mcp-exa -- uvx mcp-exa
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "daedalus-mcp-exa": {
      "type": "local",
      "command": [
        "uvx",
        "mcp-exa"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add daedalus-mcp-exa --command uvx --arg mcp-exa
# ~/.hermes/config.yaml
mcp_servers:
  daedalus-mcp-exa:
    command: "uvx"
    args: ["mcp-exa"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "daedalus-mcp-exa": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "mcp-exa"
      ]
    }
  }
}
# add to Vellum
assistant mcp add daedalus-mcp-exa -t stdio -c uvx -a mcp-exa
// mcp.json
{
  "mcpServers": {
    "daedalus-mcp-exa": {
      "command": "uvx",
      "args": [
        "mcp-exa"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 −18
    • Malware scan: pass → unverified security
    • Stability: pass → 0.80 functional
  • 17 Sept 26 +15
    • Malware scan: unverified → pass security
    • Stability: 0.97 → pass security
  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 −14
    • Malware scan: pass → unverified security
  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 10 Sept 26 0
    • Stability: 0.97 → pass security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed pypi/mcp-exa@0.1.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 34 packages
Packages resolved 34
Stale 2
No linked repository 2
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 9 exposed · ~1,012 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
answer ~104

Generate an answer to a query using Exa's search and LLM capabilities.

NameTypeReqDescription
modelThe model to use for answering (default: exa).
output_schemaJSON schema for structured output.
querystringyesThe query to answer.
system_promptA system prompt to guide the LLM's behavior.
textWhether to include full text in the results.
user_locationTwo-letter ISO country code for user location.

Structured output declared, but exposes no named fields.

No examples provided.

find_similar ~221

Find pages similar to a given URL using Exa.

NameTypeReqDescription
categoryData category to focus on.
contentsOptions for retrieving page contents. Use False to disable.
end_crawl_dateOnly links crawled before this date (YYYY-MM-DD).
end_published_dateOnly links published before this date (YYYY-MM-DD).
exclude_domainsDomains to exclude from the search.
exclude_source_domainWhether to exclude the source domain.
exclude_textStrings that must not appear in the page text.
flagsExperimental flags for Exa usage.
include_domainsDomains to include in the search.
include_textStrings that must appear in the page text.
num_resultsNumber of results to return.
start_crawl_dateOnly links crawled after this date (YYYY-MM-DD).
start_published_dateOnly links published after this date (YYYY-MM-DD).
urlstringyesThe URL to find similar pages for.

Structured output declared, but exposes no named fields.

No examples provided.

get_contents ~35

Retrieve contents for a list of URLs using Exa.

NameTypeReqDescription
urlsyesA single URL or list of URLs to retrieve contents from.

Structured output declared, but exposes no named fields.

No examples provided.

research_create ~68

Create a new research request using Exa.

NameTypeReqDescription
instructionsstringyesThe research instructions describing what to research.
modelThe model to use ('exa-research-fast', 'exa-research', 'exa-research-pro').
output_schemaJSON schema for structured output format.

Structured output declared, but exposes no named fields.

No examples provided.

research_get ~60

Get a research request by ID using Exa.

NameTypeReqDescription
eventsWhether to include events in the response.
output_schemaOptional Pydantic model for typed output validation.
research_idstringyesThe unique identifier of the research task.

Structured output declared, but exposes no named fields.

No examples provided.

research_list ~37

List research requests using Exa.

NameTypeReqDescription
cursorPagination cursor from a previous response.
limitMaximum number of results to return.

Structured output declared, but exposes no named fields.

No examples provided.

research_poll_until_finished ~96

Poll until research is finished using Exa.

NameTypeReqDescription
eventsWhether to include events in the response.
output_schemaOptional Pydantic model for typed output validation.
poll_intervalMilliseconds between polling attempts (default: 1000).
research_idstringyesThe unique identifier of the research task.
timeout_msMaximum time to wait in milliseconds (default: 600000).

Structured output declared, but exposes no named fields.

No examples provided.

search ~298

Perform a web search using Exa.

NameTypeReqDescription
additional_queriesAlternative query formulations for deep search.
categoryData category to focus on (e.g., 'company', 'news', 'research_paper').
contentsOptions for retrieving page contents. Use False to disable.
end_crawl_dateOnly links crawled before this date (YYYY-MM-DD).
end_published_dateOnly links published before this date (YYYY-MM-DD).
exclude_domainsDomains to exclude from the search.
exclude_textStrings that must not appear in the page text.
flagsExperimental flags for Exa usage.
include_domainsDomains to include in the search.
include_textStrings that must appear in the page text.
moderationIf True, moderate search results for safety.
num_resultsNumber of search results to return (default: 10).
output_schemaJSON schema for deep search structured output.
querystringyesThe search query string.
start_crawl_dateOnly links crawled after this date (YYYY-MM-DD).
start_published_dateOnly links published after this date (YYYY-MM-DD).
typeSearch type - 'auto', 'fast', 'deep', 'deep-reasoning', or 'instant'.
user_locationTwo-letter ISO country code for user location.

Structured output declared, but exposes no named fields.

No examples provided.

stream_answer ~93

Generate a streaming answer response using Exa.

NameTypeReqDescription
modelThe model to use for answering.
output_schemaJSON schema for structured output.
querystringyesThe query to answer.
system_promptA system prompt to guide the LLM's behavior.
textWhether to include full text in the results.
user_locationTwo-letter ISO country code for user location.
NameTypeReqDescription
resultarrayyes

No examples provided.

Common questions

What is the io.github.daedalus/mcp-exa server?

io.github.daedalus/mcp-exa is listed in the public MCP registry as io.github.daedalus/mcp-exa. MCP server exposing Exa websearch API. This page covers its PyPI package (mcp-exa).

Is the io.github.daedalus/mcp-exa server safe to use?

io.github.daedalus/mcp-exa scores 66 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.daedalus/mcp-exa server expose?

io.github.daedalus/mcp-exa exposes 9 tools: search, find_similar, get_contents, answer, stream_answer, and 4 more. Their descriptions and schemas cost roughly 1,012 tokens of context every time the server is loaded.

Is the io.github.daedalus/mcp-exa server still maintained?

io.github.daedalus/mcp-exa is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.daedalus/mcp-exa server under?

io.github.daedalus/mcp-exa declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.