THRONE
See report Verify server

registry / record

exa-mcp-server

npm / sealed 2026-06-16 / No. 8ae8ce16

Does exa-mcp-server MCP work in Claude Code and Cursor? Throne executed exa-mcp-server mcp in a single-use Firecracker microVM and replayed both recorded client behaviours. Compatibility verdict: fit. Is exa-mcp-server mcp safe? Static security scan: 4 finding(s) to review under security ruleset v1. The full per-step results, security findings, scan date, and evidence hash are below.

> throne registry exa-mcp-server sealed
receiptsealed evidence
scan id
8ae8ce16bfc54ac38500e5b2e893a586
target
exa-mcp-server
sealed at
2026-06-16 18:35:47Z
evidence hash
sha256:336facb2e6f8b39af150f557dee97c00684b5e27cf3b944849d84415ac4c1632
01connectPASS747ms

initialize ok: server exa-search-server 3.2.1, negotiated protocolVersion 2025-11-25, capabilities ['completions', 'prompts', 'resources', 'tools']

02discoverPASS6ms

supported: tools/list (2 tools), resources/list (1), prompts/list (1)

03validate_schemasPASS1ms

all 2 tool inputSchemas are valid JSON Schema

04smoke_test_toolsPASS242ms

called 2 of 2 tools (cap 10, strategy=serial): 0 ok, 2 returned tool-level errors (expected for synthesized args)

05error_handlingPASS4.9s

structured error responses, connection survived, wrong_type_args: web_search_exa:accepted (returned result); web_fetch_exa:accepted (returned result); unknown_method: error(-32601); invalid_id: no response (silent), connection alive; oversized_input: accepted (returned result); recovery: accepted (returned result); cancellation: accepted (returned result); old_version: accepted old version 2024-10-07, negotiated 2024-10-07, server may have stale protocol handling

06streamingNOT_APPLICABLE0ms

no streaming-capable tool declared by this server

07resource_lifecycleNOT_APPLICABLE3ms

read exa://tools/list (1 content blocks); subscribe capability not declared

08concurrent_callsWARN2ms

ladder 1 overlapping web_search_exa calls: max_observed_stable_concurrency=1; all ids answered exactly once, but every call returned an error (tool-level isError result), the tool may need runtime dependencies this sandbox does not provide

09reconnectPASS831ms

transport closed and relaunched; re-handshake ok (protocolVersion 2025-11-25, first session was 2025-11-25)

01connectPASS1.4s

initialize ok: server exa-search-server 3.2.1, negotiated protocolVersion 2025-11-25, capabilities ['completions', 'prompts', 'resources', 'tools'] [request_strategy=pipelined, connection_count=2, second connection established]

02discoverPASS8ms

supported: tools/list (2 tools), resources/list (1), prompts/list (1); notes: connection 2 confirms 2 tools

03validate_schemasPASS1ms

all 2 tool inputSchemas are valid JSON Schema

04smoke_test_toolsPASS166ms

called 2 of 2 tools (cap 10, strategy=pipelined): 0 ok, 2 returned tool-level errors (expected for synthesized args)

05error_handlingPASS5.6s

structured error responses, connection survived, wrong_type_args: web_search_exa:accepted (returned result); web_fetch_exa:accepted (returned result); unknown_method: error(-32601); invalid_id: no response (silent), connection alive; oversized_input: accepted (returned result); recovery: accepted (returned result); cancellation: accepted (returned result); old_version: accepted old version 2024-10-07, negotiated 2024-10-07, server may have stale protocol handling

06streamingNOT_APPLICABLE0ms

no streaming-capable tool declared by this server

07resource_lifecycleNOT_APPLICABLE26ms

read exa://tools/list (1 content blocks); subscribe capability not declared

08concurrent_callsWARN35ms

ladder 1/2/4/6 overlapping web_search_exa calls: max_observed_stable_concurrency=6; all ids answered exactly once, but every call returned an error (tool-level isError result), the tool may need runtime dependencies this sandbox does not provide

09reconnectPASS3.6s

transport closed and relaunched; re-handshake ok (protocolVersion 2025-11-25, first session was 2025-11-25)

chatgpt desktop calibratingemulation profile pending real-traffic captureCOMING SOON
SECURITY: REVIEW / 4 finding(s) / review recommended
LOWTHR-INSTALL-03 / Install-time script execution (npm lifecycle)

"prepare" runs on git-dependency installs and local dev (not registry installs): 'npm run build:stdio'

package/package.json
LOWTHR-NET-05 / Hardcoded outbound endpoints

8 non-local endpoint host(s) referenced in code, verify each is expected for this server's purpose: api.agnost.ai (package/smithery/stdio/index.cjs:75), api.exa.ai (package/smithery/stdio/index.cjs:80), dashboard.exa.ai (package/smithery/stdio/index.cjs:88), lodash.com (package/smithery/stdio/index.cjs:214), mcp.exa.ai (package/smithery/stdio/index.cjs:88), npms.io (package/smithery/stdio/index.cjs:19), openjsf.org (package/smithery/stdio/index.cjs:215), underscorejs.org (package/smithery/stdio/index.cjs:217)

package/smithery/stdio/index.cjs:19
LOWTHR-VER-11 / Outdated MCP SDK or protocol version pin

obsolete protocol version string '2024-10-07' in source

package/smithery/stdio/index.cjs:65
LOWTHR-VER-11 / Outdated MCP SDK or protocol version pin

obsolete protocol version string '2024-11-05' in source

package/smithery/stdio/index.cjs:65
VERDICT: FIT14 of 18 steps exercised across 2 clientsSANDBOXED RUN, submitted server executed in a disposable microVM, compatibility: 0 fail / 2 warn (14 of 18 steps exercised across 2 clients) / security: review, 4 finding(s), 0 highsealed by THRONE / No. 8ae8ce16 / 2026-06-16
scopeattestation tuple
target
exa-mcp-server npm
engine
sandboxed
claude code
calibration: partial recorded=9,spec=0,assumed=9
cursor
calibration: partial recorded=11,spec=0,assumed=7
chatgpt desktop
calibration: unavailable recorded=0,spec=2,assumed=16
steps exercised
14 of 18
test suite
v1.0.0
security ruleset
v1.0.0
sealed at
2026-06-16 18:35:47Z
evidence hash
sha256:336facb2e6f8b39af150f557dee97c00684b5e27cf3b944849d84415ac4c1632
valid until
2026-09-14
THRONE: FITwear the crown

paste this in your README. it renders the live verdict and links back to this record. if a release ever breaks the verdict, the badge says so on its own.

[![THRONE: FIT](https://api.usethrone.dev/api/badge/exa-mcp-server)](https://usethrone.dev/server/exa-mcp-server)
executed in a disposable microVM, created for this scan and destroyed after it. nothing outlives a run.

maintainer of this server? challenge this record: hello@usethrone.dev. tell us what we got wrong and we re-run it in the open.

this page renders the stored record of a real run. nothing on it is asserted without the execution that proved it.