MCP server for AnalyticDB MySQL via OpenAPI and direct SQL connection
Free
Nothing to run from here
Ainative Zerodb is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
AINative ZeroDB MCP Server - 77 operations for vector search, TurboQuant vector compression (PolarQuant + QJL), NoSQL, dedicated PostgreSQL management, files, events, RLHF, and persistent memory for AI agents with enterprise security. All tools annotated
Quickstart
# 1 — run it from where its publisher ships it
npx -y ainative-zerodb-mcp-server
# 2 — ask your agent something
> AINative ZeroDB MCP Server - 77 operations for vector search, TurboQuant vector compression (PolarQuant + QJL), NoSQL, dedicated PostgreSQL
Ainative Zerodb is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
AIAll 5 servers
ainative-studio5 servers
4 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Ainative Zerodb as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. It is scanned, signed and pinned to the version you choose — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add ainative-zerodb-mcp -- npx -y ainative-zerodb-mcp-serverReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
73 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Generate embeddings and store in ZeroDB in one step. Auto-detects dimension based on model and routes to correct storage. Use when you want to embed text and persist the vectors in a single call. Combines zerodb_generate_embeddings + zerodb_upsert_vector.
Takes no parameters.
Example callreturns →
Store agent memory in ZeroDB for persistent context. Use when the agent needs to persist conversation turns, decisions, or observations for later recall. Stores with role, session, and agent metadata for filtered retrieval.
Takes no parameters.
Example callreturns →
Get agent context window for current session. Use when the agent needs to retrieve its recent conversation context within token limits. Returns the most recent memories for a session, bounded by max_tokens.
Takes no parameters.
Example callreturns →
Store or update a vector embedding with metadata. Supports 384, 768, 1024, or 1536 dimensions. Dimension is auto-detected and validated. Use when you have a pre-computed embedding vector to store or update. For embedding text and storing in one step, use zerodb_embed_and_store instead.
Takes no parameters.
Example callreturns →
Batch upsert multiple vectors for efficiency. Use when storing many vectors at once to reduce API round-trips. Accepts an array of vector objects and processes them in a single request.
Takes no parameters.
Example callreturns →
Delete a specific vector by ID. Use when removing a single vector embedding from the store. WARNING: This operation is irreversible.
Takes no parameters.
Example callreturns →
Retrieve a specific vector by ID. Use when you need to inspect a particular vector\
Takes no parameters.
Example callreturns →
List vectors in a project/namespace with pagination. Use when the agent needs to browse or enumerate stored vectors, or answer
Takes no parameters.
Example callreturns →
Get vector statistics for a project. Use when checking how many vectors are stored, their dimensions, and namespace distribution. Returns counts, dimension breakdowns, and optionally detailed statistics.
Takes no parameters.
Example callreturns →
Create optimized index for vector search. Use when search performance needs improvement on large vector collections. Supports IVF, HNSW, and flat index types with configurable distance metrics.
Takes no parameters.
Example callreturns →
Optimize vector storage for better performance. Use when vector search is slow or storage needs compaction. Supports compress, reindex, and deduplicate operations. Use dry_run to preview changes first.
Takes no parameters.
Example callreturns →
Export vectors to various formats (JSON, CSV, Parquet). Use when you need to download or migrate vector data out of ZeroDB. Supports filtering by namespace and metadata.
Takes no parameters.
Example callreturns →
Compress vector using TurboQuant (PolarQuant + QJL) algorithm from Google Research (ICLR 2026). Achieves ~3.5x compression with 0.9999+ cosine similarity preservation. Data-oblivious — no calibration needed. Returns base64-encoded compressed data.
Takes no parameters.
Example callreturns →
Decompress a TurboQuant-compressed vector back to original dimensions. Reconstructs the full vector from the base64-encoded compressed data returned by zerodb_quantum_compress.
Takes no parameters.
Example callreturns →
Hybrid similarity search combining cosine similarity with metadata boosting. Returns ranked results with configurable weighting between similarity score and metadata relevance.
Takes no parameters.
Example callreturns →
Analyze vector space characteristics for optimal TurboQuant compression settings. Reports sparsity, magnitude distribution, and recommended precision level.
Takes no parameters.
Example callreturns →
Transform vector into feature space for enhanced similarity computation. Applies configurable feature mapping for dimensionality transformation.
Takes no parameters.
Example callreturns →
Calculate kernel similarity between two vectors. Supports fidelity (normalized dot product squared) and swap_test kernel types for measuring vector similarity.
Takes no parameters.
Example callreturns →
Create a new NoSQL table with schema. Use when you need to set up a new data structure for storing structured records. Define fields and indexes for the table schema.
Takes no parameters.
Example callreturns →
List all NoSQL tables in the project with their schemas. Use when the agent needs to discover available data structures or answer
Takes no parameters.
Example callreturns →
Get table details and schema. Use when you need to inspect a specific table\
Takes no parameters.
Example callreturns →
Delete a table and all its data. Use when a table is no longer needed and should be permanently removed. Requires confirm flag. WARNING: This operation is irreversible.
Takes no parameters.
Example callreturns →
Insert rows into a table. Use when adding new records to a NoSQL table. Accepts an array of row objects and optionally returns inserted IDs.
Takes no parameters.
Example callreturns →
Query rows from a table with filters. Use when reading data from a NoSQL table. Supports MongoDB-style filters, sorting, pagination, and field projection.
Takes no parameters.
Example callreturns →
Update rows in a table. Use when modifying existing records in a NoSQL table. Supports MongoDB-style update operators ($set, $inc, etc.) and optional upsert behavior.
Takes no parameters.
Example callreturns →
Delete rows from a table matching a filter. Use when removing specific records from a NoSQL table. Supports MongoDB-style filters. WARNING: This operation is irreversible.
Takes no parameters.
Example callreturns →
Upload file to ZeroDB storage. Use when you need to store a file (base64-encoded) in the project\
Takes no parameters.
Example callreturns →
Download file from ZeroDB storage. Use when you need to retrieve a previously uploaded file by its ID. Returns base64-encoded content by default.
Takes no parameters.
Example callreturns →
List files in project storage. Use when the agent needs to discover available files or answer
Takes no parameters.
Example callreturns →
Delete file from storage. Use when a file is no longer needed and should be permanently removed. WARNING: This operation is irreversible.
Takes no parameters.
Example callreturns →
Get file metadata without downloading content. Use when you need to check a file\
Takes no parameters.
Example callreturns →
Generate presigned URL for file access. Use when you need a temporary URL to share file access with external systems. Supports download and upload operations with configurable expiration.
Takes no parameters.
Example callreturns →
Create an event in the event stream. Use when you need to publish an event for tracking, auditing, or triggering downstream workflows. Supports event types, payloads, and correlation IDs.
Takes no parameters.
Example callreturns →
List events with filtering. Use when you need to browse or query the event stream by type, source, or time range. Supports pagination for large result sets.
Takes no parameters.
Example callreturns →
Get event details by ID. Use when you need to inspect a specific event\
Takes no parameters.
Example callreturns →
Subscribe to event stream (returns subscription ID). Use when you need to set up real-time event notifications. Supports filtering by event type and optional webhook delivery.
Takes no parameters.
Example callreturns →
Get event stream statistics. Use when you need to understand event volume, frequency, and distribution over time. Supports filtering by event type and time range.
Takes no parameters.
Example callreturns →
Create a new ZeroDB project. Use when you need to set up a new isolated workspace for storing vectors, tables, files, and events. Projects are the top-level organizational unit.
Takes no parameters.
Example callreturns →
Get project details. Use when you need to inspect a project\
Takes no parameters.
Example callreturns →
List all accessible projects. Use when the agent needs to discover available projects or answer
Takes no parameters.
Example callreturns →
Update project settings. Use when you need to modify a project\
Takes no parameters.
Example callreturns →
Delete a project and all its data. Use when a project is no longer needed. Removes all vectors, tables, files, and events within the project. Requires confirm flag. WARNING: This operation is irreversible.
Takes no parameters.
Example callreturns →
Get project usage statistics. Use when you need to check storage consumption, vector counts, API call volumes, and other usage metrics for a project.
Takes no parameters.
Example callreturns →
Enable database features for a project. Use when you need to activate specific capabilities (vectors, compression, nosql, files, events) on a project that does not yet have them enabled.
Takes no parameters.
Example callreturns →
Collect user interaction for RLHF training. Use when recording a prompt-response pair with optional feedback score for reinforcement learning. Each call creates a new training data point.
Takes no parameters.
Example callreturns →
Collect agent-level feedback. Use when recording user satisfaction signals (thumbs up/down, ratings) for a specific agent. Useful for tracking agent quality over time.
Takes no parameters.
Example callreturns →
Collect workflow-level feedback. Use when recording the outcome of a multi-step workflow including success status, duration, and steps completed.
Takes no parameters.
Example callreturns →
Collect error report for RLHF improvement. Use when recording errors encountered during agent operation to improve future behavior. Include sanitized stack traces and severity levels.
Takes no parameters.
Example callreturns →
Get RLHF collection status. Use when you need to check whether RLHF data collection is active and how many interactions have been recorded for a session.
Takes no parameters.
Example callreturns →
Get RLHF data summary and statistics. Use when you need an overview of collected RLHF data including interaction counts, average feedback scores, and trends over time.
Takes no parameters.
Example callreturns →
Start RLHF data collection for session. Use when initiating RLHF tracking at the beginning of an agent session. Safe to call multiple times — idempotent for the same session.
Takes no parameters.
Example callreturns →
Stop RLHF data collection for session. Use when ending RLHF tracking at the end of an agent session. Optionally exports collected data before stopping.
Takes no parameters.
Example callreturns →
Get RLHF interactions for a session. Use when reviewing all recorded interactions within a specific RLHF session for analysis or export.
Takes no parameters.
Example callreturns →
Broadcast RLHF event to subscribers. Use when sending RLHF-related notifications to specific agents or all subscribers. Supports targeted delivery to specific agent IDs.
Takes no parameters.
Example callreturns →
Get system-wide statistics (admin only). Use when you need a global view of platform performance and usage metrics. Requires admin privileges.
Takes no parameters.
Example callreturns →
List all projects system-wide (admin only). Use when you need to see all projects across all users for administrative purposes. Supports filtering by user ID. Requires admin privileges.
Takes no parameters.
Example callreturns →
Get user usage statistics (admin only). Use when you need to inspect a specific user\
Takes no parameters.
Example callreturns →
Get system health status (admin only). Use when you need to check the health of all system components (database, storage, search). Requires admin privileges.
Takes no parameters.
Example callreturns →
Run database optimization (admin only). Use when the database needs maintenance such as vacuum, reindex, or analyze operations. Supports dry_run to preview changes. Requires admin privileges.
Takes no parameters.
Example callreturns →
Execute SQL query on provisioned PostgreSQL instance with security validations. Use when you need to run arbitrary SQL (SELECT, INSERT, UPDATE, DELETE) against the dedicated PostgreSQL database. Supports parameterized queries and read-only mode enforcement.
Takes no parameters.
Example callreturns →
Get database schema information (tables, columns, indexes). Use when you need to discover or inspect the PostgreSQL schema structure. Returns table definitions, column types, indexes, and constraints.
Takes no parameters.
Example callreturns →
Create new PostgreSQL table with schema definition. Use when you need to define a new relational table with typed columns, constraints, and indexes. Supports if_not_exists for idempotent creation.
Takes no parameters.
Example callreturns →
Trigger PostgreSQL backup job. Use when you need to create a point-in-time backup of the database. Supports full and incremental backups with configurable retention and compression.
Takes no parameters.
Example callreturns →
Restore PostgreSQL database from backup. Use when you need to recover data from a previous backup. Supports full, schema-only, and data-only restore types. WARNING: This operation is irreversible — it overwrites existing data when confirm_overwrite is true.
Takes no parameters.
Example callreturns →
Get PostgreSQL database statistics (size, connections, query performance). Use when you need to monitor database health, connection pool usage, storage consumption, and query performance metrics.
Takes no parameters.
Example callreturns →
Provision a dedicated PostgreSQL instance via Railway with dedicated resources. Use when you need to spin up a new managed PostgreSQL database. Choose instance size based on workload requirements and budget.
Takes no parameters.
Example callreturns →
Get status and health metrics for dedicated PostgreSQL instance. Use when you need to check if your PostgreSQL instance is running, its uptime, and health indicators.
Takes no parameters.
Example callreturns →
Get connection credentials for PostgreSQL instance (database_url, host, port, etc.). Use when you need connection details to configure applications or tools. Supports primary, readonly, and admin credential types.
Takes no parameters.
Example callreturns →
Get usage statistics and billing information for PostgreSQL instance. Use when you need to review compute usage, storage consumption, and cost breakdown for your dedicated instance.
Takes no parameters.
Example callreturns →
Get SQL query logs with performance metrics and credit consumption. Use when you need to audit queries, debug slow operations, or review credit usage. Supports filtering by query type.
Takes no parameters.
Example callreturns →
Restart the dedicated PostgreSQL instance (completes in 30-60 seconds). Use when the instance needs a restart due to configuration changes or performance issues. Does not lose data.
Takes no parameters.
Example callreturns →
Delete the PostgreSQL instance and all data (requires confirmation). Use when the instance is no longer needed. Requires confirm=true. WARNING: This operation is irreversible.
Takes no parameters.
Example callreturns →
Manually renew authentication token. Use when the current auth token has expired or is about to expire and you need to force a refresh before the next API call.
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. Ainative Zerodb costs nothing to install and nothing to call, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: $8.42
$16.58 left
ATrust score 93 / 100
Release 2.3.2 · scanned 25 Aug 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings3 threat · 2 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest024b3d18382775ba21788516ca42d24412a599672663457a21af35313cabdbde
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (77 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| zerodb_generate_embeddings | no tags | |
| zerodb_embed_and_store | no tags | |
| zerodb_semantic_search | no tags | |
| zerodb_store_memory | no tags | |
| zerodb_search_memory | no tags | |
| zerodb_get_context | no tags | |
| zerodb_upsert_vector | no tags | |
| zerodb_batch_upsert_vectors | no tags | |
| zerodb_search_vectors | no tags | |
| zerodb_delete_vector | no tags | |
| zerodb_get_vector | no tags | |
| zerodb_list_vectors | untrusted-input | |
| zerodb_vector_stats | no tags | |
| zerodb_create_vector_index | no tags | |
| zerodb_optimize_vectors | no tags | |
| zerodb_export_vectors | untrusted-input | |
| zerodb_quantum_compress | no tags | |
| zerodb_quantum_decompress | no tags | |
| zerodb_quantum_hybrid_search | no tags | |
| zerodb_quantum_optimize | no tags | |
| zerodb_quantum_feature_map | no tags | |
| zerodb_quantum_kernel | no tags | |
| zerodb_create_table | no tags | |
| zerodb_list_tables | no tags | |
| zerodb_get_table | no tags | |
| zerodb_delete_table | no tags | |
| zerodb_insert_rows | no tags | |
| zerodb_query_rows | no tags | |
| zerodb_update_rows | no tags | |
| zerodb_delete_rows | no tags | |
| zerodb_upload_file | external-sink | |
| zerodb_download_file | untrusted-input | |
| zerodb_list_files | sensitive-source | |
| zerodb_delete_file | file-write | |
| zerodb_get_file_metadata | no tags | |
| zerodb_generate_presigned_url | untrusted-input | |
| zerodb_create_event | no tags | |
| zerodb_list_events | untrusted-input | |
| zerodb_get_event | no tags | |
| zerodb_subscribe_events | external-sink | |
| zerodb_event_stats | no tags | |
| zerodb_create_project | no tags | |
| zerodb_get_project | no tags | |
| zerodb_list_projects | no tags | |
| zerodb_update_project | no tags | |
| zerodb_delete_project | no tags | |
| zerodb_get_project_stats | no tags | |
| zerodb_enable_database | no tags | |
| zerodb_rlhf_interaction | no tags | |
| zerodb_rlhf_agent_feedback | no tags | |
| zerodb_rlhf_workflow | no tags | |
| zerodb_rlhf_error | no tags | |
| zerodb_rlhf_status | no tags | |
| zerodb_rlhf_summary | no tags | |
| zerodb_rlhf_start | no tags | |
| zerodb_rlhf_stop | no tags | |
| zerodb_rlhf_session | no tags | |
| zerodb_rlhf_broadcast | no tags | |
| zerodb_admin_system_stats | no tags | |
| zerodb_admin_list_projects | no tags | |
| zerodb_admin_user_usage | no tags | |
| zerodb_admin_health | no tags | |
| zerodb_admin_optimize | no tags | |
| zerodb_postgres_query | sensitive-source | |
| zerodb_postgres_schema_info | no tags | |
| zerodb_postgres_create_table | no tags | |
| zerodb_postgres_backup | no tags | |
| zerodb_postgres_restore | no tags | |
| zerodb_postgres_stats | no tags | |
| zerodb_provision_postgres | no tags | |
| zerodb_get_postgres_status | no tags | |
| zerodb_get_postgres_connection | no tags | |
| zerodb_get_postgres_usage | no tags | |
| zerodb_get_postgres_logs | sensitive-source | |
| zerodb_restart_postgres | no tags | |
| zerodb_delete_postgres | no tags | |
| zerodb_renew_token | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
A cross-tool exfiltration chain exists: zerodb_download_file → zerodb_get_postgres_logs → zerodb_subscribe_events.
Supply chain and provenance
Integrityfirst-seen
Surface digest024b3d18382775ba
Scanned2026-08-25
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Pinned to 2.3.2 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
2.3.2
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against Ainative Zerodb in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.