THRONE
See report Verify server

registry / record

@modelcontextprotocol/server-memory

npm / sealed 2026-06-16 / No. d38efb34

Does @modelcontextprotocol/server-memory MCP work in Claude Code and Cursor? Throne executed @modelcontextprotocol/server-memory mcp in a single-use Firecracker microVM and replayed both recorded client behaviours. Compatibility verdict: fit. Is @modelcontextprotocol/server-memory 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 @modelcontextprotocol/server-memory sealed
receiptsealed evidence
scan id
d38efb346d764c17b48e7f8ef7ab4862
target
@modelcontextprotocol/server-memory
sealed at
2026-06-16 17:58:10Z
evidence hash
sha256:5e5599af3294846ea50ed2391f9d4bf9f51587d397f0e415d641226c90637adf
01connectPASS816ms

initialize ok: server memory-server 0.6.3, negotiated protocolVersion 2025-11-25, capabilities ['tools']

02discoverPASS11ms

supported: tools/list (9 tools); method not found (tolerated): resources/list, prompts/list

03validate_schemasPASS3ms

all 9 tool inputSchemas are valid JSON Schema

04smoke_test_toolsPASS26ms

called 9 of 9 tools (cap 10, strategy=serial): 9 ok, 0 returned tool-level errors (expected for synthesized args)

05error_handlingPASS4.9s

structured error responses, connection survived, wrong_type_args: create_entities:accepted (returned result); create_relations:accepted (returned result); add_observations:accepted (returned result); delete_entities:accepted (returned result); delete_observations: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_APPLICABLE1ms

resources capability not declared

08concurrent_callsPASS3ms

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

09reconnectPASS823ms

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

01connectPASS1.5s

initialize ok: server memory-server 0.6.3, negotiated protocolVersion 2025-11-25, capabilities ['tools'] [request_strategy=pipelined, connection_count=2, second connection established]

02discoverPASS15ms

supported: tools/list (9 tools); method not found (tolerated): resources/list, prompts/list; notes: connection 2 confirms 9 tools

03validate_schemasPASS3ms

all 9 tool inputSchemas are valid JSON Schema

04smoke_test_toolsPASS20ms

called 9 of 9 tools (cap 10, strategy=pipelined): 9 ok, 0 returned tool-level errors (expected for synthesized args)

05error_handlingPASS4.9s

structured error responses, connection survived, wrong_type_args: create_entities:accepted (returned result); create_relations:accepted (returned result); add_observations:accepted (returned result); delete_entities:accepted (returned result); delete_observations: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_APPLICABLE1ms

resources capability not declared

08concurrent_callsPASS22ms

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

09reconnectPASS1.9s

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-INSTALL-03 / Install-time script execution (npm lifecycle)

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

package/package.json
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. d38efb34 / 2026-06-16
scopeattestation tuple
target
@modelcontextprotocol/server-memory 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 17:58:10Z
evidence hash
sha256:5e5599af3294846ea50ed2391f9d4bf9f51587d397f0e415d641226c90637adf
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/%40modelcontextprotocol%2Fserver-memory)](https://usethrone.dev/server/modelcontextprotocol-server-memory)
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.