MongoDB Connector

Connector

Available ActionsEach successful request consumes credits as outlined below.

find_documents^5crcount_documents^5crestimated_count^5crlist_databases^5crlist_collections^5craggregate^5crdistinct^5crlist_indexes^5crlist_search_indexes^5crinsert_documents^5crupdate_documents^5crreplace_document^5crfind_one_and_update^5crfind_one_and_delete^5crbulk_write^5crdelete_documents^5crcreate_index^5crdrop_index^5crcreate_search_index^5crupdate_search_index^5crdrop_search_index^5crcreate_collection^5crdrop_collection^5crrun_command^5cr

Details

Connect your own MongoDB database and query, insert, update, delete, and aggregate documents without leaving your workflow. Browse databases and collections, inspect indexes, and run full aggregation pipelines including joins, grouping, and windowed analytics. Create and manage Atlas Search indexes for full-text search and Atlas Vector Search indexes for semantic similarity and RAG applications. Export query results as downloadable CSV or JSON files for use in spreadsheets, dashboards, or data pipelines. Execute atomic find-and-modify operations and batch mixed writes in a single round trip with bulk_write. Manage collection lifecycles with create, drop, and schema validation. Access is fully permission-gated with four levels — read, write, delete, and admin — so you stay in control of what agents can do with your data. Works with MongoDB Atlas and any cloud-hosted or publicly accessible MongoDB instance.

Use Cases

Query MongoDB collections, Export data as CSV or JSON, Run aggregation pipelines, Atlas Vector Search for RAG, Full-text search with Atlas Search, Insert and update documents, Bulk write operations, Manage indexes, Create vector search indexes, Geospatial queries, Schema validation, Database administration

Connect Your Agent In 5 Min

Watch the setup guide for your platform

Or Install Locally

STDIO connector for Claude Code, Codex, Cursor, Zed, and other LLMs that require STDIO or custom connections. This lightweight connector routes requests to https://api.agentpmt.com/mcp. All tool execution happens in the cloud and the server cannot edit any files on your computer.

npm install -g @agentpmt/mcp-routeragentpmt-setup

Actions(24)

find_documents^5cr9 params(2 required)

Query documents with filter, projection, sort, and pagination. Supports CSV/JSON export.

databaserequiredstring

Database name

collectionrequiredstring

Collection name

filterobject

MongoDB query filter

projectionobject

Fields to include/exclude

sortarray

Sort as [[field, direction]] (1=asc, -1=desc)

Array of: array

limitinteger

Max documents (1-1000, default 20)

skipinteger

Documents to skip

outputarray

Output modes: inline, export, or both

Array of: string

export_formatstring

Export file format

Values:

jsoncsv

count_documents^5cr3 params(2 required)

Count documents matching a filter

databaserequiredstring

Database name

collectionrequiredstring

Collection name

filterobject

MongoDB query filter

estimated_count^5cr2 params(2 required)

Fast approximate document count using collection metadata

databaserequiredstring

Database name

collectionrequiredstring

Collection name

list_databases^5cr0 params

List all accessible databases

No parameters for this action.

list_collections^5cr1 param(1 required)

List collections in a database

databaserequiredstring

Database name

aggregate^5cr5 params(3 required)

Run an aggregation pipeline. Supports $search, $vectorSearch, $geoNear, $lookup, CSV/JSON export.

databaserequiredstring

Database name

collectionrequiredstring

Collection name

pipelinerequiredarray

Aggregation pipeline stages

Array of: object

outputarray

Output modes

Array of: string

export_formatstring

Export file format

Values:

jsoncsv

distinct^5cr4 params(3 required)

Get distinct values for a field

databaserequiredstring

Database name

collectionrequiredstring

Collection name

field_namerequiredstring

Field name

filterobject

MongoDB query filter

list_indexes^5cr2 params(2 required)

List all indexes on a collection

databaserequiredstring

Database name

collectionrequiredstring

Collection name

list_search_indexes^5cr2 params(2 required)

List Atlas Search and Vector Search indexes

databaserequiredstring

Database name

collectionrequiredstring

Collection name

insert_documents^5cr4 params(2 required)

Insert one or more documents

databaserequiredstring

Database name

collectionrequiredstring

Collection name

documentobject

Single document to insert

documentsarray

Multiple documents to insert

Array of: object

update_documents^5cr6 params(3 required)

Update one or many documents

databaserequiredstring

Database name

collectionrequiredstring

Collection name

updaterequiredobject

Update operations ($set, $inc, etc.)

filterobject

Match filter

upsertboolean

Create if no match

manyboolean

Update all matches (default: false)

replace_document^5cr5 params(3 required)

Replace a single document

databaserequiredstring

Database name

collectionrequiredstring

Collection name

documentrequiredobject

Replacement document

filterobject

Match filter

upsertboolean

Create if no match

find_one_and_update^5cr8 params(3 required)

Atomically find and update a document, returning it

databaserequiredstring

Database name

collectionrequiredstring

Collection name

updaterequiredobject

Update operations

filterobject

Match filter

projectionobject

Fields to return

sortarray

Sort to determine which doc

Array of: array

upsertboolean

Create if no match

return_documentstring

Return doc before or after update

Values:

beforeafter

find_one_and_delete^5cr5 params(2 required)

Atomically find and delete a document, returning it

databaserequiredstring

Database name

collectionrequiredstring

Collection name

filterobject

Match filter

projectionobject

Fields to return

sortarray

Sort to determine which doc

Array of: array

bulk_write^5cr3 params(3 required)

Execute mixed batch of insert, update, replace, and delete operations

databaserequiredstring

Database name

collectionrequiredstring

Collection name

operationsrequiredarray

Operations: [{operation: insert_one|update_one|update_many|replace_one|delete_one|delete_many, ...params}]

Array of: object

delete_documents^5cr4 params(2 required)

Delete one or many documents

databaserequiredstring

Database name

collectionrequiredstring

Collection name

filterobject

Match filter

manyboolean

Delete all matches (default: false)

create_index^5cr5 params(3 required)

Create an index (single, compound, text, geospatial, hashed, wildcard)

databaserequiredstring

Database name

collectionrequiredstring

Collection name

index_keysrequiredarray

Index keys [[field, 1/-1]]

Array of: array

index_namestring

Index name

index_optionsobject

Options (unique, sparse, TTL, partial, etc.)

drop_index^5cr3 params(3 required)

Drop an index from a collection

databaserequiredstring

Database name

collectionrequiredstring

Collection name

index_namerequiredstring

Index name to drop

create_search_index^5cr5 params(3 required)

Create an Atlas Search or Vector Search index

databaserequiredstring

Database name

collectionrequiredstring

Collection name

search_index_definitionrequiredobject

Search index definition (mappings or vector fields)

index_namestring

Index name

search_index_typestring

Index type (default: search)

Values:

searchvectorSearch

update_search_index^5cr4 params(4 required)

Update an Atlas Search or Vector Search index definition

databaserequiredstring

Database name

collectionrequiredstring

Collection name

index_namerequiredstring

Index name to update

search_index_definitionrequiredobject

New index definition

drop_search_index^5cr3 params(3 required)

Drop an Atlas Search or Vector Search index

databaserequiredstring

Database name

collectionrequiredstring

Collection name

index_namerequiredstring

Index name to drop

create_collection^5cr3 params(2 required)

Create a collection with optional schema validation, capping, or time series config

databaserequiredstring

Database name

collectionrequiredstring

Collection name

collection_optionsobject

Options: validator, capped, timeseries, collation, etc.

drop_collection^5cr2 params(2 required)

Drop a collection

databaserequiredstring

Database name

collectionrequiredstring

Collection name

run_command^5cr2 params(2 required)

Run any MongoDB database command (dbStats, collStats, serverStatus, etc.)

databaserequiredstring

Database name

commandrequiredobject

MongoDB command document

curl -X POST "https://api.agentpmt.com/products/purchase" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ********" \
  -d '{
    "product_id": "69c56fd1fd4227d57ee069c6",
    "parameters": {
      "action": "find_documents",
      "database": "example_database",
      "collection": "example_collection"
    }
  }'

import requests
import json

url = "https://api.agentpmt.com/products/purchase"

headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer ********"
}

data = {
    "product_id": "69c56fd1fd4227d57ee069c6",
    "parameters": {
        "action": "find_documents",
        "database": "example_database",
        "collection": "example_collection"
    }
}

response = requests.post(url, headers=headers, json=data)
print(response.status_code)
print(response.json())

const url = "https://api.agentpmt.com/products/purchase";

const headers = {
  "Content-Type": "application/json",
  "Authorization": "Bearer ********"
};

const data = {
  product_id: "69c56fd1fd4227d57ee069c6",
  parameters: {
    "action": "find_documents",
    "database": "example_database",
    "collection": "example_collection"
  }
};

fetch(url, {
  method: "POST",
  headers,
  body: JSON.stringify(data)
})
  .then(response => response.json())
  .then(data => console.log(data))
  .catch(error => console.error("Error:", error));

const axios = require('axios');

const url = "https://api.agentpmt.com/products/purchase";

const headers = {
  "Content-Type": "application/json",
  "Authorization": "Bearer ********"
};

const data = {
  product_id: "69c56fd1fd4227d57ee069c6",
  parameters: {
    "action": "find_documents",
    "database": "example_database",
    "collection": "example_collection"
  }
};

axios.post(url, data, { headers })
  .then(response => {
    console.log(response.status);
    console.log(response.data);
  })
  .catch(error => {
    console.error("Error:", error.message);
  });

Login to view your API and budget keys. The example above uses placeholder values. Sign in to see personalized code with your bearer token.

This tool supports credit-based access for external agents using AgentAddress identities or standard crypto wallets. External agents should use the External Agent API to buy credits with x402 and invoke this tool.

1. Buy Credits

Purchase credits via x402 payment (500 credit minimum, 100 credits = $1).

# Request payment requirements (returns 402 + PAYMENT-REQUIRED header)
curl -i -s -X POST "https://www.agentpmt.com/api/external/credits/purchase" \
  -H "Content-Type: application/json" \
  -d '{ "wallet_address":"0xYOUR_WALLET", "credits": 500, "payment_method":"x402" }'

# Sign the EIP-3009 authorization, then retry with signature header
curl -s -X POST "https://www.agentpmt.com/api/external/credits/purchase" \
  -H "Content-Type: application/json" \
  -H "PAYMENT-SIGNATURE: <base64-json>" \
  -d '{ "wallet_address":"0xYOUR_WALLET", "credits": 500, "payment_method":"x402" }'

2. Create a Session Nonce (nonce used in signed balance/invoke)

curl -s -X POST "https://www.agentpmt.com/api/external/auth/session" \
  -H "Content-Type: application/json" \
  -d '{ "wallet_address":"0xYOUR_WALLET" }'

3. Invoke This Tool

Sign the message with your wallet (EIP-191 personal-sign), then POST to the invoke endpoint.

# Sign this message (wallet MUST be lowercased):
# agentpmt-external
# wallet:0xyourwallet...
# session:<session_nonce>
# request:<request_id>
# action:invoke
# product:69c56fd1fd4227d57ee069c6
# payload:<sha256(canonical_json(parameters))>

curl -s -X POST "https://www.agentpmt.com/api/external/tools/69c56fd1fd4227d57ee069c6/invoke" \
  -H "Content-Type: application/json" \
  -d '{
    "wallet_address": "0xYOUR_WALLET",
    "session_nonce": "<session_nonce>",
    "request_id": "invoke-uuid",
    "signature": "0x<signature>",
    "parameters": {
      "action": "your_action",
      "your_param": "value"
    }
  }'

Usage Instructions

Usage guidance provided directly by the developer for this product.

MongoDB

Connect to a cloud-hosted MongoDB database and run queries, inserts, updates, deletes, aggregations, index management, Atlas Search, and Vector Search. Export results as CSV or JSON files. Supports MongoDB Atlas and any publicly accessible MongoDB instance.

Permissions

Access is controlled by a permissions array injected by the platform:

read (default if omitted): find, count, list, aggregate, distinct
write: insert, update, replace, find_one_and_update, bulk_write
delete: delete documents, find_one_and_delete
admin: indexes, search indexes, create/drop collection, run_command

Output Modes

find_documents and aggregate support an output array:

["inline"] (default): return documents in the response
["export"]: save results as a file (CSV or JSON)
["inline", "export"]: both

Use export_format to choose csv or json (default: json).

Read Actions

`find_documents`

Required: database, collection Optional: filter, projection, sort ([[field, 1/-1]]), limit (1-1000, default 20), skip, output, export_format

Example: {"action":"find_documents","database":"mydb","collection":"users","filter":{"status":"active"},"limit":10}

`count_documents`

Required: database, collection Optional: filter

`estimated_count`

Required: database, collection Fast approximate count using collection metadata (no filter support).

`list_databases`

No required params.

`list_collections`

Required: database

`aggregate`

Required: database, collection, pipeline Optional: output, export_format

Supports all pipeline stages including $search, $vectorSearch, $geoNear, $lookup, $graphLookup, $sample.

Example: {"action":"aggregate","database":"mydb","collection":"orders","pipeline":[{"$group":{"_id":"$status","count":{"$sum":1}}}]}

Vector search example: {"action":"aggregate","database":"mydb","collection":"docs","pipeline":[{"$vectorSearch":{"index":"vector_idx","path":"embedding","queryVector":[0.1,0.2,...],"numCandidates":100,"limit":10}}]}

`distinct`

Required: database, collection, field_name Optional: filter

`list_indexes`

Required: database, collection Returns all indexes on a collection with key specs, options, and names.

`list_search_indexes`

Required: database, collection Returns Atlas Search and Vector Search indexes.

Write Actions

`insert_documents`

Required: database, collection, document (single) or documents (array)

`update_documents`

Required: database, collection, update Optional: filter, upsert, many (default false)

`replace_document`

Required: database, collection, document Optional: filter, upsert

`find_one_and_update`

Atomically find and update a document, returning it. Required: database, collection, update Optional: filter, projection, sort, upsert, return_document ("before" or "after", default "before")

`find_one_and_delete`

Atomically find and delete a document, returning it. Required: database, collection Optional: filter, projection, sort

`bulk_write`

Execute mixed batch operations in a single round trip. Required: database, collection, operations

Each operation: {"operation": "insert_one|update_one|update_many|replace_one|delete_one|delete_many", ...params}

Example: {"action":"bulk_write","database":"mydb","collection":"users","operations":[{"operation":"insert_one","document":{"name":"Alice"}},{"operation":"update_one","filter":{"name":"Bob"},"update":{"$set":{"active":true}}}]}

Delete Actions

`delete_documents`

Required: database, collection Optional: filter, many (default false)

Admin Actions

`create_index`

Required: database, collection, index_keys Optional: index_name, index_options

Supports all index types: single field, compound, text ([["field","text"]]), geospatial ([["location","2dsphere"]]), hashed, wildcard.

`drop_index`

Required: database, collection, index_name

`create_search_index`

Create an Atlas Search or Vector Search index. Required: database, collection, search_index_definition Optional: index_name, search_index_type ("search" or "vectorSearch")

Vector index example: {"action":"create_search_index","database":"mydb","collection":"docs","search_index_type":"vectorSearch","index_name":"vec_idx","search_index_definition":{"fields":[{"type":"vector","path":"embedding","numDimensions":1536,"similarity":"cosine"}]}}

`update_search_index`

Required: database, collection, index_name, search_index_definition

`drop_search_index`

Required: database, collection, index_name

`create_collection`

Required: database, collection Optional: collection_options (validator, capped, timeseries, clusteredIndex, collation, expireAfterSeconds)

`drop_collection`

Required: database, collection

`run_command`

Run any MongoDB database command. Required: database, command

Example: {"action":"run_command","database":"mydb","command":{"dbStats":1}} Example: {"action":"run_command","database":"mydb","command":{"collStats":"users"}}

Notes

Filters use standard MongoDB query syntax: $eq, $gt, $lt, $in, $regex, $near, $geoWithin, etc.
Updates use $set, $unset, $inc, $push, $pull, etc.
Sort uses 1 for ascending, -1 for descending
Aggregation pipelines with $out or $merge require write permission
Max 1000 documents returned per find or aggregate call
Atlas Search and Vector Search require search indexes (use create_search_index)
Geospatial queries require 2dsphere or 2d indexes (use create_index)

MongoDB Connector

Available ActionsEach successful request consumes credits as outlined below.

Details

Use Cases

Connect Your Agent In 5 Min

Or Install Locally

Related Content

MongoDB Connector: AI Infrastructure for Database Agents

Looking for help integrating AI into your business? Set up a free consultation.