THRONE
See report Verify server

registry / record

duckduckgo-mcp-server

uvx / sealed 2026-06-16 / No. 8b328fe3

Does duckduckgo-mcp-server MCP work in Claude Code and Cursor? Throne executed duckduckgo-mcp-server mcp in a single-use Firecracker microVM and replayed both recorded client behaviours. Compatibility verdict: fit. Is duckduckgo-mcp-server mcp safe? Static security scan: 1 finding(s) to review under security ruleset v1. The full per-step results, security findings, scan date, and evidence hash are below.

> throne registry duckduckgo-mcp-server sealed
receiptsealed evidence
scan id
8b328fe3eeb24ea2a038c14ba9b9d9e1
target
uvx duckduckgo-mcp-server
sealed at
2026-06-16 19:05:03Z
evidence hash
sha256:e778df9ae6d7167633e609db2720c5559c3bbbb011ce52fbf5dffb88a56542e1
01connectPASS1.1s

initialize ok: server ddg-search 1.27.2, negotiated protocolVersion 2025-11-25, capabilities ['experimental', 'prompts', 'resources', 'tools']

02discoverPASS19ms

supported: tools/list (2 tools), resources/list (0), prompts/list (0)

03validate_schemasPASS8ms

all 2 tool inputSchemas are valid JSON Schema

04smoke_test_toolsPASS838ms

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

05error_handlingPASS5.6s

structured error responses, connection survived, wrong_type_args: search:accepted (returned result); fetch_content:accepted (returned result); unknown_method: error(-32602); 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 2025-11-25, server may have stale protocol handling

06streamingNOT_APPLICABLE0ms

no streaming-capable tool declared by this server

07resource_lifecycleNOT_APPLICABLE6ms

server declares resources but lists none

08concurrent_callsPASS621ms

ladder 1 overlapping search calls: max_observed_stable_concurrency=1; all ids answered exactly once at every level

09reconnectPASS1.1s

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

01connectPASS1.8s

initialize ok: server ddg-search 1.27.2, negotiated protocolVersion 2025-11-25, capabilities ['experimental', 'prompts', 'resources', 'tools'] [request_strategy=pipelined, connection_count=2, second connection established]

02discoverPASS30ms

supported: tools/list (2 tools), resources/list (0), prompts/list (0); notes: connection 2 confirms 2 tools

03validate_schemasPASS7ms

all 2 tool inputSchemas are valid JSON Schema

04smoke_test_toolsPASS852ms

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

05error_handlingPASS5.4s

structured error responses, connection survived, wrong_type_args: search:accepted (returned result); fetch_content:accepted (returned result); unknown_method: error(-32602); 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 2025-11-25, server may have stale protocol handling

06streamingNOT_APPLICABLE0ms

no streaming-capable tool declared by this server

07resource_lifecycleNOT_APPLICABLE4ms

server declares resources but lists none

08concurrent_callsPASS1.2s

ladder 1/2/4/6 overlapping search calls: max_observed_stable_concurrency=6; all ids answered exactly once at every level

09reconnectPASS2.0s

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 / 1 finding(s) / review recommended
LOWTHR-NET-05 / Hardcoded outbound endpoints

1 non-local endpoint host(s) referenced in code, verify each is expected for this server's purpose: html.duckduckgo.com (duckduckgo_mcp_server-0.4.0/src/duckduckgo_mcp_server/server.py:55)

duckduckgo_mcp_server-0.4.0/src/duckduckgo_mcp_server/server.py:55
VERDICT: FIT14 of 18 steps exercised across 2 clientsSANDBOXED RUN, submitted server executed in a disposable microVM, compatibility: 0 fail / 0 warn (14 of 18 steps exercised across 2 clients) / security: review, 1 finding(s), 0 highsealed by THRONE / No. 8b328fe3 / 2026-06-16
scopeattestation tuple
target
uvx duckduckgo-mcp-server pypi
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 19:05:03Z
evidence hash
sha256:e778df9ae6d7167633e609db2720c5559c3bbbb011ce52fbf5dffb88a56542e1
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/uvx%20duckduckgo-mcp-server)](https://usethrone.dev/server/duckduckgo-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.