com.mcparmory/parallel
PYPI · MCPARMORY-PARALLEL · 2 COMPONENTS · SCANNED SEP 20
Search the web, extract content, and run distributed tasks with AI-powered automation
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security87
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Install-script risk not yet assessed.Unverified
- 2 of 41 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: the license (MIT License) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 131 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability73
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 3554 tokens (~148/item across 24 items; 24 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 24 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
How do I install the com.mcparmory/parallel MCP server?
com.mcparmory/parallel runs locally as a PyPI package, launched with uvx mcparmory-parallel. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · mcparmory-parallel
claude mcp add com-mcparmory-parallel -- uvx mcparmory-parallel
{
"mcpServers": {
"com-mcparmory-parallel": {
"command": "uvx",
"args": [
"mcparmory-parallel"
]
}
}
} {
"servers": {
"com-mcparmory-parallel": {
"command": "uvx",
"args": [
"mcparmory-parallel"
]
}
}
} codex mcp add com-mcparmory-parallel -- uvx mcparmory-parallel
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"com-mcparmory-parallel": {
"type": "local",
"command": [
"uvx",
"mcparmory-parallel"
],
"enabled": true
}
}
} openclaw mcp add com-mcparmory-parallel --command uvx --arg mcparmory-parallel
mcp_servers:
com-mcparmory-parallel:
command: "uvx"
args: ["mcparmory-parallel"] {
"McpServers": {
"com-mcparmory-parallel": {
"Transport": "stdio",
"Command": "uvx",
"Arguments": [
"mcparmory-parallel"
]
}
}
} assistant mcp add com-mcparmory-parallel -t stdio -c uvx -a mcparmory-parallel
{
"mcpServers": {
"com-mcparmory-parallel": {
"command": "uvx",
"args": [
"mcparmory-parallel"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 19 Sept 26 −3
- Stability: pass → 0.80 functional
- 18 Sept 26 +16
- Malware scan: unverified → pass ▲ security
- Stability: 0.97 → pass security
- 17 Sept 26 −15
- Malware scan: pass → unverified ▼ security
- 16 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 14 Sept 26 −14
- Malware scan: pass → unverified ▼ security
- 12 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Sept 26 −4
- Stability: pass → 0.77 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed pypi/mcparmory-parallel@1.0.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
Background: How many MCP packages publish verified provenance →
Dependencies 41 packages
| Packages resolved | 41 |
|---|---|
| Stale | 1 |
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
add_runs_to_task_group Add Runs to Task Group ~182
Initiates multiple task runs within a TaskGroup, allowing batch execution of tasks with specified inputs and output requirements.
| Name | Type | Req | Description |
|---|---|---|---|
| input_schema | – | – | Optional JSON schema or text description specifying the expected input structure for tasks. A plain string is treated as a text schema with that description. |
| inputs | array | yes | Array of task run configurations to execute. Each item represents a single task run with its input parameters. Up to 1,000 runs can be added per request; for larger batches, split across multiple req… |
| output_schema | – | yes | JSON schema or text description defining the desired output structure from each task. Field descriptions in the schema will determine the form and content of task responses. A plain string is treated… |
| taskgroup_id | string | yes | The unique identifier of the TaskGroup to which runs will be added. |
No output schema declared.
No examples provided.
create_findall_run Create FindAll Run ~242
Initiates a FindAll run to search for entities matching specified criteria. Returns immediately with a queued run object; use the returned run ID to poll status, stream events, or receive webhook notifications as the search progresses.
| Name | Type | Req | Description |
|---|---|---|---|
| entity_type | string | yes | The category or type of entity to search for (e.g., company, person, product). |
| exclude_list | array | – | Optional list of entity names or IDs to exclude from the search results. |
| generator | string | yes | The search algorithm tier to use: 'base' for basic matching, 'core' for standard accuracy, 'pro' for advanced matching, or 'preview' for experimental features. |
| match_conditions | array | yes | Array of conditions that entities must satisfy to be included in results. Order and format depend on the entity type and generator used. |
| match_limit | integer | yes | Maximum number of matching entities to return, between 5 and 1000 inclusive. |
| metadata | object | – | Optional custom metadata object to attach to the FindAll run for tracking or reference purposes. |
| objective | string | yes | The goal or search objective described in natural language for the FindAll run. |
No output schema declared.
No examples provided.
create_findall_spec_from_objective Create FindAll Spec From Objective ~93
Converts a natural language search objective into a structured FindAll specification that can be used to execute targeted searches. The generated spec serves as a customizable starting point and can be further refined by the user.
| Name | Type | Req | Description |
|---|---|---|---|
| objective | string | yes | A natural language description of what you want to find. Describe your search goal in plain English, such as company characteristics, funding criteria, or other business attributes you're looking for. |
No output schema declared.
No examples provided.
create_monitor Create Monitor ~286
Create a web monitor that periodically executes a search query at a specified frequency and sends updates to an optional webhook. The monitor runs immediately upon creation and then continues according to the configured schedule.
| Name | Type | Req | Description |
|---|---|---|---|
| cadence | string | – | Deprecated: use the 'frequency' field instead. Predefined execution cadence options: hourly, daily, weekly, or every two weeks. |
| frequency | string | – | How often the monitor should execute, specified as a number followed by a time unit: 'h' for hours, 'd' for days, or 'w' for weeks (e.g., '1h', '2d', '1w'). Must be between 1 hour and 30 days inclusi… |
| metadata | object | – | Optional custom metadata object to store application-specific context with the monitor. This metadata is returned in webhook notifications and GET requests, allowing you to correlate monitor response… |
| output_schema | – | – | Optional schema definition for structuring the monitor's output events. Defines how results should be formatted in webhook notifications. |
| query | string | yes | The search query to monitor for material changes. This query will be executed periodically according to the monitor's frequency. |
| webhook | object | – | Optional webhook URL that will receive notifications whenever the monitor executes, including execution results and any detected changes. |
No output schema declared.
No examples provided.
create_task_group Create Task Group ~84
Creates a new TaskGroup to organize and monitor multiple task runs together. Use this to establish a logical grouping for related tasks that should be tracked as a unit.
| Name | Type | Req | Description |
|---|---|---|---|
| metadata | object | – | Optional custom metadata to attach to the task group for organizational or tracking purposes. This metadata is stored with the group and can be used to add context or labels relevant to your use case. |
No output schema declared.
No examples provided.
create_task_run Create Task Run ~528
Initiates a new task run that processes input according to a specified processor and output schema. Returns immediately with a run object in 'queued' status. Supports optional filtering by domain, date range, and webhook notifications.
| Name | Type | Req | Description |
|---|---|---|---|
| after_date | string | – | Filter results to content published on or after this date. Provide as an RFC 3339 date string in YYYY-MM-DD format. |
| enable_events | boolean | – | Enable or disable progress event tracking for this run. When true, execution progress events are recorded and accessible via the Task Run events endpoint. Defaults to true for premium processors. Req… |
| event_types | array | – | List of event types that trigger webhook notifications. Defaults to empty array (no notifications sent). |
| exclude_domains | array | – | Exclude results from specific domains. Accepts full domains (e.g., example.com, subdomain.example.gov) or domain extensions with leading period (e.g., .gov, .edu, .co.uk). Sources matching these doma… |
| include_domains | array | – | Restrict results to specific domains. Accepts full domains (e.g., example.com, subdomain.example.gov) or domain extensions with leading period (e.g., .gov, .edu, .co.uk). Only sources matching these… |
| input | – | yes | The input data for the task, provided as either plain text or a JSON object matching the input schema. |
| input_schema | – | – | Optional JSON schema or text description of the expected input format. A plain string is treated as a text schema with that description. |
| mcp_servers | array | – | Optional list of MCP servers to use for this run. Requires 'mcp-server-2025-07-17' in the parallel-beta header to enable. |
| metadata | object | – | Custom key-value metadata to attach to the run. Keys and values must be strings, with keys limited to 16 characters and values to 512 characters. |
| output_schema | – | yes | JSON schema or text description defining the desired output structure and content. Field descriptions determine the form and content of the response. A plain string is treated as a text schema. |
| previous_interaction_id | string | – | Reference to a previous interaction to use as context for this task run, enabling multi-turn workflows. |
| processor | string | yes | The processor type to execute the task. Use 'base' for standard processing. |
| url | string | yes | Webhook URL where task run notifications will be sent. |
No output schema declared.
No examples provided.
delete_monitor Delete Monitor ~44
Permanently delete a monitor and stop all its future executions. Deleted monitors cannot be updated or retrieved.
| Name | Type | Req | Description |
|---|---|---|---|
| monitor_id | string | yes | The unique identifier of the monitor to delete. |
No output schema declared.
No examples provided.
extract_content_from_urls Extract Content from URLs ~188
Extracts relevant content from specified web URLs, optionally focused on a search objective or keyword queries.
| Name | Type | Req | Description |
|---|---|---|---|
| excerpts | – | – | Whether to include excerpts from each URL relevant to the search objective and queries. Enabled by default. Most useful when objective or search_queries are specified; redundant if neither is provide… |
| full_content | – | – | Whether to include the complete content from each URL. Disabled by default. Enable to retrieve full page content; useful when objective and search_queries are not specified. |
| objective | string | – | Optional search objective to focus extraction on specific topics or themes. When provided, helps filter extracted content to relevant sections. |
| search_queries | array | – | Optional list of keyword search queries to focus extraction. When provided, extracted content will prioritize sections matching these queries. |
| urls | array | yes | List of web URLs to extract content from. Each URL should be a valid HTTP or HTTPS address. |
No output schema declared.
No examples provided.
get_event_group Get Event Group ~69
Retrieve a specific event group associated with a monitor. The response contains event items that represent individual events within the group.
| Name | Type | Req | Description |
|---|---|---|---|
| event_group_id | string | yes | The unique identifier of the event group to retrieve. |
| monitor_id | string | yes | The unique identifier of the monitor that contains the event group. |
No output schema declared.
No examples provided.
get_monitor Get Monitor ~49
Retrieve a specific monitor by its ID. Returns the complete monitor configuration including status, cadence, input settings, and webhook configuration.
| Name | Type | Req | Description |
|---|---|---|---|
| monitor_id | string | yes | The unique identifier of the monitor to retrieve. |
No output schema declared.
No examples provided.
get_task_group_run Get Task Group Run ~80
Retrieves the status and details of a specific task group run by its run ID. The run result data is available separately via the `/result` endpoint.
| Name | Type | Req | Description |
|---|---|---|---|
| run_id | string | yes | The unique identifier of the run whose status and details should be retrieved. |
| taskgroup_id | string | yes | The unique identifier of the task group containing the run. |
No output schema declared.
No examples provided.
get_task_run Get Task Run ~54
Retrieve the status and details of a specific task run by its ID. Use the `/result` endpoint to access the run's output results.
| Name | Type | Req | Description |
|---|---|---|---|
| run_id | string | yes | The unique identifier of the task run to retrieve. |
No output schema declared.
No examples provided.
get_task_run_input Get Task Run Input ~61
Retrieves the input data that was provided to a specific task run. Use this to inspect what parameters or data were passed when the task run was executed.
| Name | Type | Req | Description |
|---|---|---|---|
| run_id | string | yes | The unique identifier of the task run whose input you want to retrieve. |
No output schema declared.
No examples provided.
get_task_run_result Get Task Run Result ~59
Retrieves the result of a completed task run by its ID. This operation blocks until the task run finishes executing, then returns the final result.
| Name | Type | Req | Description |
|---|---|---|---|
| run_id | string | yes | The unique identifier of the task run whose result you want to retrieve. |
No output schema declared.
No examples provided.
get_taskgroup Get Task Group ~49
Retrieves a TaskGroup and its aggregated status across all runs, providing a summary view of the group's execution state.
| Name | Type | Req | Description |
|---|---|---|---|
| taskgroup_id | string | yes | The unique identifier of the TaskGroup to retrieve. |
No output schema declared.
No examples provided.
list_monitor_events List Monitor Events ~127
Retrieve events for a specific monitor, including errors and material changes from up to the last 300 event groups. Events are returned in reverse chronological order with the most recent first.
| Name | Type | Req | Description |
|---|---|---|---|
| lookback_period | string | – | The time window to search for events, specified as a duration (e.g., '10d' for 10 days, '1w' for 1 week). Supports day and week increments with a minimum of 1 day. Defaults to 10 days if not specifie… |
| monitor_id | string | yes | The unique identifier of the monitor for which to retrieve events. |
No output schema declared.
No examples provided.
list_monitors List Monitors ~103
Retrieve all active monitors for the user with their current configuration and status. Supports cursor-based pagination to efficiently browse large monitor lists.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of monitors to return per request, between 1 and 10,000. Omit to retrieve all monitors at once. |
| monitor_id | string | – | Cursor for pagination—specify a monitor ID to start listing after that point in lexicographic order. Useful for fetching subsequent pages of results. |
No output schema declared.
No examples provided.
list_monitors_paginated List Monitors Paginated ~117
Retrieve a paginated list of active monitors ordered by creation time, newest first. Use cursor-based pagination to navigate through results.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | Opaque token for cursor-based pagination. Omit this parameter to start from the most recently created monitor, or provide the `next_cursor` value from a previous response to fetch the next page of re… |
| limit | integer | – | Maximum number of monitors to return per page. Must be between 1 and 10,000, defaults to 100 if not specified. |
No output schema declared.
No examples provided.
list_task_group_runs List Task Group Runs ~197
Retrieves all task runs within a TaskGroup as a resumable stream, with optional inclusion of run inputs and outputs.
| Name | Type | Req | Description |
|---|---|---|---|
| include_input | boolean | – | Include the input data for each run in the stream response. Defaults to false. |
| include_output | boolean | – | Include the output data for each run in the stream response. Defaults to false. |
| last_event_id | string | – | Resume a stream from a specific point by providing the event_id of the last received event. The stream will continue from the next event after this cursor. |
| status | string | – | Filter runs by their current status: queued (waiting to start), action_required (awaiting user input), running (in progress), completed (finished successfully), failed (encountered an error), cancell… |
| taskgroup_id | string | yes | The unique identifier of the TaskGroup whose runs should be retrieved. |
No output schema declared.
No examples provided.
search_web Search Web ~416
Search the web for information based on natural language objectives or keyword queries. Returns relevant results with excerpts optimized for the specified use case.
| Name | Type | Req | Description |
|---|---|---|---|
| after_date | string | – | Start date for filtering results, provided as an RFC 3339 date string. Only content published on or after this date will be included. |
| exclude_domains | array | – | List of domains to exclude from results. Accepts full domains (e.g., example.com, subdomain.example.gov) or domain extensions with leading period (e.g., .gov, .edu). Sources from specified domains wi… |
| include_domains | array | – | List of domains to restrict results to. Accepts full domains (e.g., example.com, subdomain.example.gov) or domain extensions with leading period (e.g., .gov, .edu). Only sources from specified domain… |
| max_chars_per_result | integer | – | Maximum characters to include per URL in excerpts. Values below 1000 are automatically increased to 1000. Excerpts may be shorter to prioritize relevance and token efficiency. |
| max_chars_total | integer | – | Maximum total characters across all results combined. Values below 1000 are automatically increased to 1000. This limit applies in addition to the per-result limit to maximize relevance and token eff… |
| max_results | integer | – | Maximum number of results to return. Defaults to 10 if not specified. |
| mode | string | – | Execution mode that presets parameter defaults for different use cases: 'one-shot' for comprehensive single-response answers, 'agentic' for token-efficient results in multi-step workflows, or 'fast'… |
| objective | string | – | Natural language description of the search objective, including any preferences about source types or content freshness. Either this or search_queries must be provided. |
| search_queries | array | – | List of traditional keyword search queries to guide the search, optionally including search operators. Either this or objective must be provided. |
No output schema declared.
No examples provided.
simulate_monitor_event Simulate Monitor Event ~133
Simulate sending an event to a monitor to test its event handling and triggering behavior. Useful for validating monitor configurations without waiting for real events.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | – | Optional binary payload data to include with the simulated event. |
| event_type | string | – | The type of event to simulate. Defaults to `monitor.event.detected` if not specified. Valid options are: `monitor.event.detected` (standard event detection), `monitor.execution.completed` (successful… |
| monitor_id | string | yes | The unique identifier of the monitor to simulate an event for. |
No output schema declared.
No examples provided.
stream_task_group_events Stream Task Group Events ~97
Streams real-time events from a TaskGroup, including status updates and run completions. The connection remains open for up to one hour while at least one run in the group is active.
| Name | Type | Req | Description |
|---|---|---|---|
| last_event_id | string | – | Optional event ID to resume streaming from a specific point, useful for recovering from connection interruptions without missing events. |
| taskgroup_id | string | yes | The unique identifier of the TaskGroup whose events should be streamed. |
No output schema declared.
No examples provided.
stream_task_run_events Stream Task Run Events ~58
Stream events for a specific task run, including progress updates and state changes. Event frequency is reduced for task runs created without event streaming enabled.
| Name | Type | Req | Description |
|---|---|---|---|
| run_id | string | yes | The unique identifier of the task run for which to retrieve events. |
No output schema declared.
No examples provided.
update_monitor Update Monitor ~238
Update an existing monitor's configuration, including its search query, check frequency, webhook URL, and associated metadata. At least one field must be provided to apply changes.
| Name | Type | Req | Description |
|---|---|---|---|
| event_types | array | – | Event types that should trigger webhook notifications. Specify as an array of event type identifiers. |
| frequency | string | – | Updated check frequency for the monitor. Specify as a number followed by a unit: 'h' for hours, 'd' for days, or 'w' for weeks. Must be between 1 hour and 30 days inclusive. |
| metadata | object | – | Custom metadata object to associate with the monitor. This metadata is included in all webhook notifications, allowing you to correlate monitor events with corresponding objects in your application. |
| monitor_id | string | yes | The unique identifier of the monitor to update. |
| query | string | – | Updated search query for the monitor. Use for minor prompt and instruction refinements only; major query changes may affect change detection accuracy since the monitor compares new results against pr… |
| url | string | yes | The webhook URL where monitor notifications will be sent. Must be a valid HTTPS or HTTP endpoint. |
No output schema declared.
No examples provided.
What is the com.mcparmory/parallel MCP server?
com.mcparmory/parallel is an MCP server listed in the public MCP registry as com.mcparmory/parallel. Search the web, extract content, and run distributed tasks with AI-powered automation. This page covers its PyPI package (mcparmory-parallel).
Is the com.mcparmory/parallel MCP server safe to use?
com.mcparmory/parallel scores 75 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the com.mcparmory/parallel MCP server expose?
com.mcparmory/parallel exposes 24 tools: search_web, extract_content_from_urls, create_task_run, get_task_run, get_task_run_input, and 19 more. Their descriptions and schemas cost roughly 3,554 tokens of context every time the server is loaded.
Is the com.mcparmory/parallel MCP server still maintained?
com.mcparmory/parallel is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.