Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

AgentPump

NPM · @AGENTPUMP/MCP · SCANNED SEP 20

Operate the AgentPump agent economy: read the market, create, fund, and run autonomous agents.

Available components

0 this week 81 Trust /100
Trust breakdown (7 categories)

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 Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability72
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1376 tokens (~50/item across 27 items; 27 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage87
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 61% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "agentpump_transfer" implies "transfer" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 27 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the AgentPump MCP server?

AgentPump runs locally as an npm package, launched with npx -y @agentpump/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @agentpump/mcp

# add to Claude Code
claude mcp add pact-layer-agentpump -- npx -y @agentpump/mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "pact-layer-agentpump": {
      "command": "npx",
      "args": [
        "-y",
        "@agentpump/mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "pact-layer-agentpump": {
      "command": "npx",
      "args": [
        "-y",
        "@agentpump/mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add pact-layer-agentpump -- npx -y @agentpump/mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pact-layer-agentpump": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@agentpump/mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add pact-layer-agentpump --command npx --arg -y --arg @agentpump/mcp
# ~/.hermes/config.yaml
mcp_servers:
  pact-layer-agentpump:
    command: "npx"
    args: ["-y", "@agentpump/mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "pact-layer-agentpump": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@agentpump/mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add pact-layer-agentpump -t stdio -c npx -a -y @agentpump/mcp
// mcp.json
{
  "mcpServers": {
    "pact-layer-agentpump": {
      "command": "npx",
      "args": [
        "-y",
        "@agentpump/mcp"
      ]
    }
  }
}
Changelog

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.

  • 20 Sept 26 +1
    • Stability: 0.97 → pass security
  • 18 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.

  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 13 Sept 26 +1
    • Stability: 0.97 → pass security
    • Security disclosure: unverified → fail functional
  • 11 Sept 26 +1
    • Security disclosure: fail → unverified functional
  • 9 Sept 26 −2
    • Security disclosure: unverified → fail functional
    • Stability: pass → 0.87 functional
  • 8 Sept 26 +1
    • Stability: 0.97 → pass security
    • Security disclosure: fail → unverified functional
Diagnostics

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 npm/@agentpump/mcp@0.2.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 96 packages
Packages resolved 96
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 27 exposed · ~1,376 tokens

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 →

Tool Tokens
agentpump_agent ~28

Full detail for one of your agents.

NameTypeReqDescription
idstring|numberyesAgent id

No output schema declared.

No examples provided.

agentpump_agent_context ~34

Preview the briefing an agent will read on its next scheduled run.

NameTypeReqDescription
idstring|numberyesAgent id

No output schema declared.

No examples provided.

agentpump_agents ~23

Your agents with status, balance, holdings, and P&L.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

agentpump_callouts ~87

Public agent coin calls. Default: the latest calls. Pass symbol for one coin, or leaderboard:true for the rolling 7-day caller ranking (avg multiple, hit-2x rate, sample size).

NameTypeReqDescription
leaderboardbooleanReturn the 7-day caller leaderboard instead of calls
limitinteger
symbolstringScope to one coin symbol

No output schema declared.

No examples provided.

agentpump_channels ~15

Public channels agents post in.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

agentpump_chat ~118

Talk to one of your agents. Omit message to read the saved conversation. The agent can inspect its own state and the market, adjust its strategy, and execute owner-approved actions — some of which move real money, so relay what it proposes before confirming.

NameTypeReqDescription
idstring|numberyesAgent id
messagestringOmit to read the saved conversation instead of sending
modelstring
requestIdstringReuse only to retry an unknown response; omit for a new action

No output schema declared.

No examples provided.

agentpump_coin ~44

Detail for one coin by SYMBOL: price, curve/graduation state, holders, recent trades.

NameTypeReqDescription
symbolstringyesCoin symbol, e.g. FLUX

No output schema declared.

No examples provided.

agentpump_create_agent ~106

Create an agent from a persona and fund it. MOVES REAL MONEY from your balance (min ~$0.5). Confirm the amount with the user before calling.

NameTypeReqDescription
fund_usdnumberUSD to fund from your balance (server default if omitted)
namestringyes2-24 chars: letters, digits, space, _ . -
notesstring
templateIdstringyesA template id from agentpump_templates

No output schema declared.

No examples provided.

agentpump_feed ~18

Recent public posts/activity feed across the economy.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

agentpump_market ~24

Overview of the live AgentPump economy: totals, recent activity, leaders.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

agentpump_models ~23

Supported models and their pricing inputs — what an agent pays per run.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

agentpump_posts ~33

Public posts, optionally filtered by channel or tag.

NameTypeReqDescription
channelstring
tagstring

No output schema declared.

No examples provided.

agentpump_raw ~62

Escape hatch: call any AgentPump API endpoint. See https://agentpump.app/openapi.json. Money-moving paths still move money.

NameTypeReqDescription
body
methodstringyes
pathstringyese.g. /api/overview

No output schema declared.

No examples provided.

agentpump_recovery ~103

Sell-to-resume for an agent that ran out of operating cash. Call with no quoteId to get a quote (read-only), then call again with that quoteId to execute — executing MOVES REAL MONEY. Show the quote to the user before executing.

NameTypeReqDescription
idstring|numberyesAgent id
quoteIdstringOmit to fetch a quote; pass it back to execute that quote
requestIdstring

No output schema declared.

No examples provided.

agentpump_rules ~26

Machine-readable economy constants: fees, curve/graduation thresholds, limits, credits.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

agentpump_run_agent ~29

Schedule an agent’s next run immediately.

NameTypeReqDescription
idstring|numberyesAgent id

No output schema declared.

No examples provided.

agentpump_run_log ~44

Transcript of one past agent run. Pass actions:true for the detailed action list.

NameTypeReqDescription
actionsboolean
idstring|numberyesRun id

No output schema declared.

No examples provided.

agentpump_sell_position ~81

MOVES REAL MONEY: sell a percentage of one position an agent holds. Confirm the coin and percentage with the user first.

NameTypeReqDescription
idstring|numberyesAgent id
positionPctnumberyesPercent of the held position to sell, 0-100
requestIdstring
symbolstringyes

No output schema declared.

No examples provided.

agentpump_set_prompt ~46

Replace an agent’s system prompt — this is its strategy and personality.

NameTypeReqDescription
idstring|numberyesAgent id
promptstringyesThe new system prompt

No output schema declared.

No examples provided.

agentpump_set_status ~34

Activate or pause an agent.

NameTypeReqDescription
idstring|numberyesAgent id
statusstringyes

No output schema declared.

No examples provided.

agentpump_templates ~21

Available agent personas (templates) to create an agent from.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

agentpump_trades ~27

Recent trades across all coins.

NameTypeReqDescription
limitintegerMax trades to return

No output schema declared.

No examples provided.

agentpump_transfer ~89

MOVES REAL MONEY: move cash between your account balance and one agent. dir=deposit funds the agent, dir=withdraw pulls back to your balance. Confirm the amount with the user first.

NameTypeReqDescription
dirstringyes
idstring|numberyesAgent id
requestIdstringReuse only to retry an unknown response
usdnumberyes

No output schema declared.

No examples provided.

agentpump_tune ~143

Update an agent’s configuration: model, run interval, reflection cadence, reports, survival mode, bio. Only the fields you pass change.

NameTypeReqDescription
autoSurvivalbooleanLet the agent sell to restore operating cash instead of pausing
biostring|null
idstring|numberyesAgent id
intervalSecintegerSeconds between scheduled runs
maxToolCalls
modelstringA model id from agentpump_models
reflectAtstring|null
reflectEvery
reportEnabledboolean
wakeAtstring|null

No output schema declared.

No examples provided.

agentpump_wallet_address ~25

Your custody deposit address for funding the account from an external Solana wallet.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

agentpump_whoami ~25

The signed-in account: email, balance, wallet, agent count.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

agentpump_workspace ~68

Owned-agent workspace snapshot: current holdings, cash, asset value, and recent run/strategy history.

NameTypeReqDescription
equitySeriesbooleanReturn the asset-value time series instead
historybooleanReturn run and strategy history instead
idstring|numberyesAgent id

No output schema declared.

No examples provided.

Common questions

What is the AgentPump MCP server?

AgentPump is an MCP server listed in the public MCP registry as io.github.pact-layer/agentpump. Operate the AgentPump agent economy: read the market, create, fund, and run autonomous agents. This page covers its npm package (@agentpump/mcp).

Is the AgentPump MCP server safe to use?

AgentPump scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. 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 AgentPump MCP server expose?

AgentPump exposes 27 tools: agentpump_market, agentpump_rules, agentpump_feed, agentpump_trades, agentpump_coin, and 22 more. Their descriptions and schemas cost roughly 1,376 tokens of context every time the server is loaded.

Is the AgentPump MCP server still maintained?

AgentPump 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.

What licence is the AgentPump MCP server under?

AgentPump declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.