Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
Nothing to run from here
Agentx 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.
83/100
trust score
2
downloads a day
local
runs on your machine
110
downloads in 30d
What it does
Local-first agent factory MCP Server for Claude Code with enhanced features
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user agentx-mcp '--' npx -y agentx-mcp
# 2 — ask your agent for something these tools do
# list_agents, get_agent, create_agent and 46 more
Agentx costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
AMAll 1 server
agentx-mcp1 server
1 category
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 Agentx 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. Its scan result is on the Security tab — 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. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user agentx-mcp '--' npx -y agentx-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
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
49 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.
List all agents - Returns all agent assets with their metadata
No parameter schema on file.
Get an agent by id - Returns metadata and parsed AgentConfig YAML
No parameter schema on file.
Create a new agent - Creates and registers a new agent with YAML config
No parameter schema on file.
Update an agent - Updates agent metadata (name, description, tags)
No parameter schema on file.
Delete an agent - Permanently removes an agent from the database
No parameter schema on file.
Export an agent - Exports agent to CLAUDE.md + settings.json files
No parameter schema on file.
Batch delete multiple assets by IDs with dependency checking
No parameter schema on file.
Batch add tags to multiple assets
No parameter schema on file.
Batch remove tags from multiple assets
No parameter schema on file.
Clone an asset to create a duplicate with a new name
No parameter schema on file.
Check if an asset can be safely deleted (no dependents)
No parameter schema on file.
Get all assets that depend on the given asset
No parameter schema on file.
Get all assets that the given asset depends on
No parameter schema on file.
Get the full dependency graph for an asset (recursive)
No parameter schema on file.
Detect circular dependencies starting from an asset
No parameter schema on file.
Export all assets (or filtered by type) in various formats: claude, zip, json, yaml
No parameter schema on file.
Import skills, rules, or prompts from Claude Code local directories (~/.claude/skills, ~/.claude/prompts) into AgentX
No parameter schema on file.
List all MCP servers - Returns all MCP server configuration assets
No parameter schema on file.
Get an MCP server by id - Returns metadata and parsed McpConfig
No parameter schema on file.
Create a new MCP server - Creates and registers a new MCP server config
No parameter schema on file.
Update an MCP server - Updates MCP server metadata
No parameter schema on file.
Delete an MCP server - Permanently removes an MCP server from the database
No parameter schema on file.
List all prompts - Returns all prompt assets with their metadata
No parameter schema on file.
Get a prompt by id - Returns metadata and raw content
No parameter schema on file.
Create a new prompt - Creates and registers a new prompt asset
No parameter schema on file.
Update a prompt - Updates prompt metadata and/or content
No parameter schema on file.
Delete a prompt - Permanently removes a prompt from the database
No parameter schema on file.
List all rules - Returns all rule assets with their metadata
No parameter schema on file.
Get a rule by id - Returns metadata and raw content
No parameter schema on file.
Create a new rule - Creates and registers a new rule asset
No parameter schema on file.
Update a rule - Updates rule metadata and/or content
No parameter schema on file.
Delete a rule - Permanently removes a rule from the database
No parameter schema on file.
Search assets - Full-text search across all assets by name, description, and content
No parameter schema on file.
List all skills - Returns all skill assets in the database with their metadata
No parameter schema on file.
Get a skill by id - Returns a single skill asset by its unique identifier
No parameter schema on file.
Create a new skill - Creates and registers a new skill asset
No parameter schema on file.
Update a skill - Updates skill metadata and/or content
No parameter schema on file.
Delete a skill - Permanently removes a skill from the database
No parameter schema on file.
Create a version snapshot of an asset
No parameter schema on file.
List all version snapshots for an asset
No parameter schema on file.
Get a specific version snapshot
No parameter schema on file.
Rollback an asset to a specific version
No parameter schema on file.
Clear all version history for an asset
No parameter schema on file.
Get version statistics for an asset
No parameter schema on file.
List all workflows - Returns all workflow assets with their metadata
No parameter schema on file.
Get a workflow by id - Returns metadata and raw content
No parameter schema on file.
Create a new workflow - Creates and registers a new workflow asset
No parameter schema on file.
Update a workflow - Updates workflow metadata and/or content
No parameter schema on file.
Delete a workflow - Permanently removes a workflow from the database
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under ISC
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Agentx or to call it, 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: —
BTrust score 83 / 100
Release 2.0.1 · scanned 14 Oct 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 score91
Client score83
Findings10 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationnone
Surface digest8f0cdc1bfaed299cd62d03aa2e554745f22efddc9bb3c29fb39404286a8f2c2e
Score vectorthreat 91 → client 83
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | none | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read | −2 |
| 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 surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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 |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
can start a fixed program (a process-spawning capability, not arbitrary code execution)
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.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest8f0cdc1bfaed299c
Scanned2026-10-14
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
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 2.0.1. Pin a release below and the command asks for exactly that one.
2.0.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Agentx can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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 a signed-in account that does not publish it, and nothing else.