Model Context Protocol server for Rollbar
Nothing to run from here
AgentWatch 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.
21
tools declared
—
trust score
remote
at its publisher
—
calls last 7d
What it does
Read-only watchtower for AI agents on-chain: decoded receipts, plan vs execution, Safe audits.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http agentwatch-agentwatch-mcp https://agentwatch.agentwatch.workers.dev/mcp
# 2 — ask your agent for something these tools do
# list_watched, get_feed, run_audit and 18 more
AgentWatch costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
AGAll 1 server
agentwatch1 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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http agentwatch-agentwatch-mcp https://agentwatch.agentwatch.workers.dev/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: 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 pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
21 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 watched addresses for this connector principal. NEW USERS: if empty, call watch_demo_set next (do not invent a global feed), then get_dashboard.
No parameter schema on file.
Decoded activity feed for an address. Use when reviewing what an agent did on-chain.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | yes | Watched address (0x…40 hex) |
| since | number | no | Unix seconds lower bound |
Run provenance audit on a Safe/address. Use when the user asks 'is this fake?' or wants a shareable verdict.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | yes | Safe/address to audit (0x…40 hex) |
| chain | string | no | — |
| agents | string | no | Comma-separated agent keys |
Blast-radius / historical capability for an agent key. Use before trusting an agent with funds.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_key | string | yes | — |
List alerts scoped to this principal's watched addresses (empty watch list → call watch_demo_set first). Use when checking what needs attention.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | — |
Pending Safe multisig proposals from the Safe Transaction Service (indexer confidence). Pass safe=0x… or omit to scan all watched addresses.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| safe | string | no | Optional Safe address; default = all watched |
| chains | string | no | Optional comma-separated chain ids |
Intent↔execution fidelity score for an agent or Safe. Use for accountability / coverage meter. Check matched_agent — false means the address has no indexed activity (as signer or as the Safe that executed), so the score is vacuous.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_key | string | yes | Agent EOA address (0x…40 hex) |
Public standings for agents with a published passport, ranked from receipts (declared-first coverage, fidelity, reliability, hygiene, sustained work). Pass agent_key to get that agent's own rank, its component scores, and what it would need to climb. Read-only: nothing here can be self-reported.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_key | string | no | Optional: address to locate in the standings |
| limit | number | no | How many ranked rows to return (default 10, max 50) |
Counterfactual P&L / agent alpha vs do-nothing baselines. Use for performance honesty checks. Check matched_agent — false means the key has no indexed activity.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_key | string | yes | Agent EOA address (0x…40 hex) |
TCA market-context snapshot for an event_id (chain:txHash). Use when judging execution quality.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| event_id | string | yes | — |
Declare an intent BEFORE broadcasting. Returns {intent_id, pairing_code}. Append the 16-hex pairing_code as the last 8 bytes of calldata (no magic prefix), then broadcast — EXCEPT bare ETH transfers to contracts (empty data + value>0): appending reverts on Safe/fallback handlers; register without a suffix and use expected.steps for multi-leg flows (e.g. approve+supply). Pairing codes are single-us
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_key | string | yes | — |
| description | string | yes | — |
| declared_at | number | no | — |
| deadline_minutes | number | no | Relative window; stored as absolute constraints.deadline |
| expected | object | no | Structured shape. Use steps: ['approve','other'] (or similar) so one intent covers approve+supply/swap companions. |
Start watching an address. Use when onboarding a new agent or Safe.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | yes | Address to watch (0x…40 hex) |
| chains | string | no | — |
| label | string | no | Optional short label (e.g. Agent EOA) |
ONE-SHOT cold-start for brand-new Claude / MCP users with an empty watch list. Adds the July 18 fixture (Agent EOA + Safe A + Safe B on Base, with declared intents) and one live Polygon trading bot, so the first dashboard has recent activity. Call this FIRST after connect when list_watched is empty, then call get_dashboard (Always allow the App). Idempotent — skips addresses already watched.
No parameter schema on file.
Force an immediate poller pass over this principal's watched addresses (catch up txs from explorers into AgentWatch). Use after add_watch / a fresh broadcast when get_feed is still empty. Optional address / chains to focus the pass.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | no | Optional single address to refresh (0x…40 hex) |
| chains | string | no | Optional csv of chains (default: ethereum,base first, then the rest) |
Read the declared identity of a watched agent (name, model provider, how often it runs, role, purpose, operator) and whether its public passport page is published.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | yes | Watched agent address (0x…40 hex) |
Declare who a watched agent is: model provider, run cadence, role, purpose, operator, and whether to publish a shareable public passport at /a/<slug>. Declarations never change the receipt-derived numbers next to them; publishing exposes only this address, never the rest of the watch list.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | yes | Watched agent address (0x…40 hex) |
| display_name | string | no | Name shown instead of the raw address |
| provider | string | no | Which model drives the agent |
| model | string | no | Optional model or framework detail |
| cadence | string | no | always_on, scheduled, event_driven, on_demand |
| role | string | no | — |
| purpose | string | no | One or two sentences on what it is for |
| operator | string | no | Who runs it |
| public | boolean | no | Publish a public passport page |
List this user's saved recovery wallets (human co-signers for default 1/2 Safes). Each may have a label/purpose — users often keep several for different vaults.
No parameter schema on file.
Save or update a recovery address for this user. Product default Safe is then 1/2: threshold 1, owners = [agent, this recovery]. Use make_default=true to prefer this label in get_safe_defaults.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | yes | 0x recovery wallet the human controls |
| label | string | no | Short name, e.g. hardware, treasury, personal |
| purpose | string | no | What this recovery is for, e.g. default, trading |
| make_default | boolean | no | Prefer this label for default Safes |
Remove a saved recovery address for this user.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | yes | — |
Return the default Safe ownership plan for an agent EOA: threshold 1 + agent + selected recovery (1/2 when one recovery is set). Call before register_intent for Safe deploys. AgentWatch never deploys or signs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_key | string | yes | Agent EOA that will be an owner/signer |
| recovery_label | string | no | Optional label to pick among several recoveries |
| purpose | string | no | Optional purpose filter (e.g. trading) |
| chain | string | no | Optional chain hint for the intent constraints |
| all_recoveries | boolean | no | If true, include all matching recoveries (1/n) instead of just the default one |
Persona-tailored dashboard brief (fidelity, alerts, pending plans, recent planned-vs-executed). NEW USERS with empty watches: call watch_demo_set first, then get_dashboard again. Narrate in plain language; ask the user to Always allow the AgentWatch MCP App widget when the host prompts.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| persona | string | no | Optional override; otherwise uses saved persona |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 AgentWatch 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: —
—Grade not published
No rule-by-rule report on file for this release
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.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.5.1.
0.5.1
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 AgentWatch 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.