legacy-mongodb-mcp
Provides read-only access to legacy MongoDB instances (<4.0) via the Model Context Protocol, enabling AI models to query databases, collections, and run aggregations safely.
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
Webxspark
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.
list_databasesList all databases for a MongoDB connection. Returns: JSON object with array of database names, sizes, and total size
list_collectionsList all collections for a given database. Args: database: Database name Returns: JSON object with array of collection names
findRun a find query against a MongoDB collection. Args: database: Database name collection: Collection name filter: The query filter, matching the syntax of db.collection.find() projection: The projection, matching the syntax of db.collection.find() limit: The maximum number of documents to return (def…
countGets the number of documents in a MongoDB collection. Uses db.collection.count() with query as an optional filter parameter. Args: database: Database name collection: Collection name query: Optional filter to count matching documents Returns: JSON object with document count
aggregateRun an aggregation against a MongoDB collection. Note: $vectorSearch is NOT supported in legacy MongoDB (<4.0). Args: database: Database name collection: Collection name pipeline: An array of aggregation stages to execute responseBytesLimit: Maximum bytes to return in response Returns: JSON object w…
collection_indexesDescribe the indexes for a collection. Args: database: Database name collection: Collection name Returns: JSON object with array of index definitions
collection_schemaDescribe the schema for a collection by sampling documents. Args: database: Database name collection: Collection name sampleSize: Number of documents to sample for schema inference (default: 50) responseBytesLimit: Maximum bytes to return in response Returns: Inferred schema with field types and sta…
collection_storage_sizeGets the size of the collection. Args: database: Database name collection: Collection name Returns: Collection storage statistics
db_statsReturns statistics that reflect the use state of a single database. Args: database: Database name Returns: Database statistics
explainReturns statistics describing the execution of the winning plan chosen by the query optimizer. Args: database: Database name collection: Collection name method: The method and its arguments to run as a 2-element array: [method_name, args_dict] where method_name is "find", "aggregate", or "count" Exa…
export_dataExport a query or aggregation results in the specified EJSON format. Args: database: Database name collection: Collection name exportTitle: A short description to uniquely identify the export exportTarget: The export target as a 2-element array: [target_name, args_dict] where target_name is "find" o…
mongodb_logsReturns the most recent logged mongod events. Args: type: The type of logs to return (global or startupWarnings) limit: The maximum number of log entries to return (default: 50, max: 1024) Returns: Array of log entries
get_server_configGet the current server configuration (with sensitive data redacted). Returns: Server configuration and connection status
MDB_MCP_READ_ONLYNo true Enable read-only mode (always true for this server)MDB_MCP_INDEX_CHECKNo false Reject queries that don't use an indexMDB_MCP_MAX_DOCUMENTS_PER_QUERYNo 100 Maximum documents per queryMDB_MCP_MAX_BYTES_PER_QUERYNo 16777216 Maximum response bytes (16MB)MDB_MCP_LOG_LEVELNo INFO Logging level (DEBUG, INFO, WARNING, ERROR)MDB_MCP_CONNECTION_STRINGTool 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
13/13 tools missing one or more hints — list_databases (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_collections (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); find (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +10 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.
Descriptions match behaviour
1 tool describes read intent but its handler mutates — export_data (line 1046: with open(filepath, 'w', encoding='utf-8') as f:)
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
11/13 tool handlers declare input schemas (85%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
12/13 tool handlers wrap calls in try/catch (92%)
Wrap each tool handler body in try/catch and return a structured error response.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tests exist
No test files found
Add tests that exercise each declared tool.
Tool description accuracy
export_data: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
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/webxspark/legacy-mongodb-mcp)?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