registry / record
mcp-server-fetch
Does mcp-server-fetch MCP work in Claude Code and Cursor? Throne executed mcp-server-fetch mcp in a single-use Firecracker microVM and replayed both recorded client behaviours. Compatibility verdict: fit. Is mcp-server-fetch mcp safe? Static security scan: no findings under security ruleset v1. The full per-step results, security findings, scan date, and evidence hash are below.
> throne registry mcp-server-fetch
sealed
- scan id
- 95e17513af7d46deaed3d5e28491a345
- target
- uvx mcp-server-fetch
- sealed at
- 2026-06-16 19:17:56Z
- evidence hash
- sha256:1b5c39a64d8663b2d1a67d77a91d4e5788f08ec483fb76412f707c0854b51433
initialize ok: server mcp-fetch 1.27.2, negotiated protocolVersion 2025-11-25, capabilities ['experimental', 'prompts', 'tools']
supported: tools/list (1 tools), prompts/list (1); method not found (tolerated): resources/list
all 1 tool inputSchemas are valid JSON Schema
called 1 of 1 tools (cap 10, strategy=serial): 0 ok, 1 returned tool-level errors (expected for synthesized args)
structured error responses, connection survived, wrong_type_args: fetch: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
no streaming-capable tool declared by this server
resources capability not declared
ladder 1 overlapping fetch 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
transport closed and relaunched; re-handshake ok (protocolVersion 2025-11-25, first session was 2025-11-25)
initialize ok: server mcp-fetch 1.27.2, negotiated protocolVersion 2025-11-25, capabilities ['experimental', 'prompts', 'tools'] [request_strategy=pipelined, connection_count=2, second connection established]
supported: tools/list (1 tools), prompts/list (1); method not found (tolerated): resources/list; notes: connection 2 confirms 1 tools
all 1 tool inputSchemas are valid JSON Schema
called 1 of 1 tools (cap 10, strategy=pipelined): 0 ok, 1 returned tool-level errors (expected for synthesized args)
structured error responses, connection survived, wrong_type_args: fetch: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
no streaming-capable tool declared by this server
resources capability not declared
ladder 1/2/4/6 overlapping fetch 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
transport closed and relaunched; re-handshake ok (protocolVersion 2025-11-25, first session was 2025-11-25)
- target
- uvx mcp-server-fetch 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 19:17:56Z
- evidence hash
- sha256:1b5c39a64d8663b2d1a67d77a91d4e5788f08ec483fb76412f707c0854b51433
- valid until
- 2026-09-14
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.
[](https://usethrone.dev/server/mcp-server-fetch)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.