registry / record
@upstash/context7-mcp
Does @upstash/context7-mcp MCP work in Claude Code and Cursor? Throne executed @upstash/context7-mcp mcp in a single-use Firecracker microVM and replayed both recorded client behaviours. Compatibility verdict: fit. Is @upstash/context7-mcp 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 @upstash/context7-mcp
sealed
- scan id
- 4604084c572f4eaba489da83f9dc09ed
- target
- @upstash/context7-mcp
- sealed at
- 2026-06-16 18:29:32Z
- evidence hash
- sha256:5965c54899d04788018e989e1af2a5b5673f8b37dc09ae7b9d29e9465a65ffff
initialize ok: server Context7 3.2.1, negotiated protocolVersion 2025-11-25, capabilities ['prompts', 'resources', 'tools']
supported: tools/list (2 tools), resources/list (0), prompts/list (0)
all 2 tool inputSchemas are valid JSON Schema
called 2 of 2 tools (cap 10, strategy=serial): 2 ok, 0 returned tool-level errors (expected for synthesized args)
structured error responses, connection survived, wrong_type_args: resolve-library-id:accepted (returned result); query-docs: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
no streaming-capable tool declared by this server
server declares resources but lists none
ladder 1 overlapping resolve-library-id calls: max_observed_stable_concurrency=1; all ids answered exactly once at every level
transport closed and relaunched; re-handshake ok (protocolVersion 2025-11-25, first session was 2025-11-25)
initialize ok: server Context7 3.2.1, negotiated protocolVersion 2025-11-25, capabilities ['prompts', 'resources', 'tools'] [request_strategy=pipelined, connection_count=2, second connection established]
supported: tools/list (2 tools), resources/list (0), prompts/list (0); notes: connection 2 confirms 2 tools
all 2 tool inputSchemas are valid JSON Schema
called 2 of 2 tools (cap 10, strategy=pipelined): 2 ok, 0 returned tool-level errors (expected for synthesized args)
structured error responses, connection survived, wrong_type_args: resolve-library-id:accepted (returned result); query-docs: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
no streaming-capable tool declared by this server
server declares resources but lists none
ladder 1/2/4/6 overlapping resolve-library-id calls: max_observed_stable_concurrency=6; all ids answered exactly once at every level
transport closed and relaunched; re-handshake ok (protocolVersion 2025-11-25, first session was 2025-11-25)
3 non-local endpoint host(s) referenced in code, verify each is expected for this server's purpose: context7.com (package/dist/index.js:104), login.microsoftonline.com (package/dist/lib/jwt.js:10), mcp.context7.com (package/dist/lib/constants.js:8)
package/dist/index.js:104- target
- @upstash/context7-mcp 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 18:29:32Z
- evidence hash
- sha256:5965c54899d04788018e989e1af2a5b5673f8b37dc09ae7b9d29e9465a65ffff
- 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/upstash-context7-mcp)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.