Cordelia Proxy (seed-drill/cordelia-proxy) is an MCP server listed on the M8ven Trust Index. It scores 26 out of 100, grade F. It declares 21 tools. No publisher has claimed this listing.
MCP server for memory storage, encryption, search, and group sharing, used by Claude Code via the cordelia-agent-sdk.
Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
seed-drill
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
memory_read_hotRead L1 hot context for a user. Returns dense structured memory including identity, active state, preferences, and delegation rules. Load this at session start.
memory_write_hotWrite to L1 hot context for a user. Use patch for partial updates, replace for full replacement. Supports optimistic concurrency via expected_updated_at.
memory_statusGet memory system status and available users.
memory_analyze_noveltyAnalyze text for novelty signals. Returns detected signals, confidence scores, and suggested persistence targets. Use this to determine what from a conversation should be persisted to memory.
memory_searchSearch L2 warm index by keyword, type, and/or tags. Returns matching entries with relevance scores. Use this to find entities, sessions, or learnings from memory.
memory_read_warmRead a specific L2 warm item by ID. Returns the full item content (entity, session, or learning).
memory_write_warmCreate or update an L2 warm item. Use for storing entities (people, orgs, projects, concepts), session summaries, or learnings (patterns, insights, principles).
memory_delete_warmDelete a specific L2 warm item by ID. Removes the item from storage and the index.
memory_backupCreate a backup of the memory database. Returns backup manifest with SHA-256 verification. SQLite provider only.
memory_restoreRestore memory database from a backup. Verifies SHA-256, runs integrity checks, migrates schema if needed. SQLite provider only.
memory_shareShare a private memory to a group. Creates an immutable copy; the original is never modified.
memory_group_createCreate a new group. The calling entity becomes owner.
memory_group_listList groups, optionally filtered by entity membership.
memory_group_readRead group details including members.
memory_group_add_memberAdd a member to a group. Requires admin/owner role.
memory_group_remove_memberRemove a member from a group. Requires admin/owner role.
memory_bind_contextBind a working directory to a group. Writes from that directory will be scoped to the group, and searches will prioritize group memories. Stored in L1 active.context_bindings.
memory_unbind_contextRemove a context binding for a working directory. Restores default behavior (private memory).
memory_backfill_embeddingsRebuild FTS and vec indexes from L2 items. Rebuilds FTS keyword index (includes details field) and vec embeddings. Uses cached embeddings where available, generates new ones via Ollama.
memory_reconcileReconcile search index with node storage. Indexes replicated items that arrived via P2P but are missing from local FTS5/vec search. Runs automatically on startup and every 60s, but can be triggered manually.
memory_prefetch_l2Prefetch top L2 items for faster session start. Returns most recently accessed items from user groups and private memory. Context-aware: prioritizes bound group if context binding exists.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Prometheus exporter process crash via malformed HTTP request
Prometheus exporter process crash via malformed HTTP request
CORDELIA_API_KEYCORDELIA_BASE_URLCORDELIA_CONTEXT_WINDOWCORDELIA_CORE_APICORDELIA_CREDENTIALSCORDELIA_CREDENTIALS_FILECORDELIA_EMBEDDING_MODELnomic-embed-textCORDELIA_EMBEDDING_PROVIDERollamaCORDELIA_EMBEDDING_URLhttp://localhost:11434CORDELIA_HOMECORDELIA_HTTP_HOSTCORDELIA_HTTP_PORTCORDELIA_INTEGRITY_INTERVAL_MSCORDELIA_LOCAL_USERSCORDELIA_MEMORY_ROOTCORDELIA_NODE_TOKENCORDELIA_NODE_URLCORDELIA_REMOTE_URLCORDELIA_SESSION_SECRETCORDELIA_STORAGEsqliteCORDELIA_TTL_SWEEP_INTERVAL_MS3600000FLY_APP_NAMEFLY_REGIONGITHUB_CLIENT_IDGITHUB_CLIENT_SECRETHONEYCOMB_API_KEYHONEYCOMB_DATASETHOSTOTEL_SERVICE_NAMEPORTAL_URLSENTRY_DSNTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
21/21 tools missing one or more hints — memory_read_hot (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); memory_write_hot (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); memory_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +18 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool test coverage
Only 0/21 tools referenced in tests (0%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
1 call in production code run through a shell (hooks/recovery.mjs:19)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Secrets not logged
3 secret values sent to error/log
Redact or omit secret values from log output.
Production dependencies are patched
0 critical, 2 high severity in production deps — @opentelemetry/auto-instrumentations-node@0.69.0 (high), @opentelemetry/sdk-node@0.211.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dependency freshness
1/18 production deps stale: swagger-ui-express@2024-05-31 (2.3y)
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/seed-drill/cordelia-proxy)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check