THRONE
See report Verify server

registry / record

mcp-server-fetch

uvx / sealed 2026-06-12 / No. d23ed7c1

> throne registry mcp-server-fetch sealed
receiptsealed evidence
scan id
d23ed7c1e74546539c79334311426dd2
target
uvx mcp-server-fetch
sealed at
2026-06-12 06:48:29Z
evidence hash
sha256:084e03be21885290377c92e99683a5cceeee6347a6a060d4d7edd1b981d94734
01connectPASS627ms

initialize ok: server mcp-fetch 1.27.2, negotiated protocolVersion 2025-11-25, capabilities ['experimental', 'prompts', 'tools']

02discoverPASS6ms

supported: tools/list (1 tools), prompts/list (1); method not found (tolerated): resources/list

03validate_schemasPASS4ms

all 1 tool inputSchemas are valid JSON Schema

04smoke_test_toolsPASS7ms

called 1 of 1 tools (cap 10): 0 ok, 1 returned tool-level errors (expected for synthesized args)

05error_handlingPASS4.0s

structured error responses, connection survived — wrong_type_args: accepted (returned result); unknown_method: error(-32602); invalid_id: no response (silent), connection alive

06streamingPASS0ms

no streaming-capable tool declared by this server; not applicable (pass-na)

07resource_lifecyclePASS6ms

resources capability not declared; not applicable (pass-na)

08concurrent_callsWARN51ms

ladder 1/2/4/8 overlapping fetch calls: max_observed_stable_concurrency=8; 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

09reconnectPASS827ms

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

01connectPASS639ms

initialize ok: server mcp-fetch 1.27.2, negotiated protocolVersion 2025-11-25, capabilities ['experimental', 'prompts', 'tools']

02discoverPASS8ms

supported: tools/list (1 tools), prompts/list (1); method not found (tolerated): resources/list

03validate_schemasPASS3ms

all 1 tool inputSchemas are valid JSON Schema

04smoke_test_toolsPASS6ms

called 1 of 1 tools (cap 10): 0 ok, 1 returned tool-level errors (expected for synthesized args)

05error_handlingPASS3.8s

structured error responses, connection survived — wrong_type_args: accepted (returned result); unknown_method: error(-32602); invalid_id: no response (silent), connection alive

06streamingPASS0ms

no streaming-capable tool declared by this server; not applicable (pass-na)

07resource_lifecyclePASS3ms

resources capability not declared; not applicable (pass-na)

08concurrent_callsWARN63ms

ladder 1/2/4/8 overlapping fetch calls: max_observed_stable_concurrency=8; 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

09reconnectPASS780ms

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

chatgpt desktopemulation profile pending real-traffic captureCOMING SOON
SECURITY: CLEAN / no findings
VERDICT: FIT TO SHIPSANDBOXED RUN — submitted server executed in a disposable microVM — compatibility: 0 fail / 2 warn across 2 clients / security: clean, 0 findingssealed by THRONE / No. d23ed7c1 / 2026-06-12
THRONE: FIT TO SHIPwear 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 TO SHIP](https://api.usethrone.dev/api/badge/uvx%20mcp-server-fetch)](https://usethrone.dev/server/mcp-server-fetch)
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.