neurostack
Local RAG layer and optimizer for your Markdown knowledge base. CLI + MCP server: grounded answers for any AI client, stale-note detection, session harvesting into memories. Local-first.
Caution. Specific findings reduced this grade. They are listed on the page. 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
raphasouthall
Source: Glama · also listed on github_repo_search
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.
wrappervault_read_fileRead a markdown file from the vault.
vault_list_filesList markdown files under a vault directory.
vault_write_fileCreate or overwrite a markdown file in the vault. Commits + pushes to origin/main.
vault_delete_fileDelete a markdown file from the vault. Commits + pushes to origin/main.
session_briefGet a compact ~500 token session brief.
vault_contextAssemble task-scoped context for session recovery after /clear or new conversation.
vault_rememberSave a memory - persist an observation, decision, or learning for future retrieval.
vault_forgetDelete a specific memory by ID.
vault_update_memoryUpdate an existing memory. Only provided fields are changed.
vault_mergeMerge two memories. Source is folded into target; source is deleted.
vault_memoriesSearch or list agent-written memories.
vault_searchSearch the vault.
vault_askAsk a natural language question and get an answer with citations from vault content.
vault_summaryGet pre-computed summary for a note by path or search query.
vault_graphGet wiki-link neighborhood for a note with summaries and PageRank.
vault_graph_analysisFind structural gaps and bridge notes in the wiki-link graph.
vault_relatedFind semantically related notes using embedding similarity.
vault_triplesSearch knowledge graph triples for structured facts.
vault_communitiesAnswer global queries using GraphRAG community summaries.
vault_diffShow what changed in the vault: additions, modifications, deletions.
vault_checkpointRecord the current vault state as a named diff baseline.
vault_statsGet index health: note count, embedding coverage, graph stats, triple stats.
vault_record_usageRecord that specific notes were retrieved and used in this session.
vault_prediction_errorsReturn prediction errors — note or memory signals that surprised at retrieval.
vault_session_startStart a new memory session to group related memories.
vault_session_endEnd a memory session and optionally generate a summary.
vault_harvestExtract insights from recent AI coding sessions and save as memories.
NEUROSTACK_MODEcurl -fsSL https://raw.githubusercontent.com/raphasouthall/neurostack/main/install.sh =lite bashNEUROSTACK_DB_PATHCODEX_HOMENEUROSTACK_WORKSPACETool 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
29/29 tools missing one or more hints — wrapper (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); vault_read_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); vault_list_files (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +26 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.
Destructive tools are labelled
1 tool perform destructive updates without destructiveHint — vault_delete_file deletes at line 507 (abs_path.unlink())
Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.
Tool inputs are validated
27/28 tool handlers declare input schemas (96%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 7/28 tool handlers wrap calls in try/catch (25%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests exist
No test files found
Add tests that exercise each declared tool.
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/raphasouthall/neurostack)?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