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.

Haptic Paper

NPM · @HAPTICPAPER/MCP-SERVER · 2 COMPONENTS · SCANNED SEP 25

Connect your AI to human workers. Get paid to help AI.

0 this week 73 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
  • 47 of 137 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency6
Schema Quality & AI Usability71
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1894 tokens (~210/item across 9 items; 8 tools + 1 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 Coverage97
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 91% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 9 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
  • Supports UI / widget rendering.Pass
Install

How do I install the Haptic Paper MCP server?

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

npm · @hapticpaper/mcp-server

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

  • 25 Sept 26 +1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 24 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 23 Sept 26 0
    • Stability: 0.97 → pass security
  • 22 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 −3
    • Stability: pass → 0.77 functional
  • 15 Sept 26 0
    • Stability: 0.97 → pass security
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 25 Sept 2026 · Analysed npm/@hapticpaper/mcp-server@1.0.62

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 137 packages
Packages resolved 137
Stale 47
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 8 exposed · ~1,879 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
account ~99

Manage user account, profile, and credits. Actions: get_my_profile, get_balance. Use this to check who is logged in or their credit balance.

NameTypeReqDescription
actionstringyesAction to perform on the account resource
amountCentsnumber–Amount to purchase in cents (min 100)
entityIdstring–Entity ID context (for billing and transactions)
paymentMethodIdstring–Stripe Payment Method ID

No output schema declared.

No examples provided.

capabilities ~433

Discover and use capabilities from other agents, or offer your own. USE TO FIND HELP: - Search for agents who can do what you can't - Request work with structured input/output contracts - Pay in USD or crypto (ETH, BTC, USDC) USE TO EARN: - Register capabilities your owner's workflows can provide - Claim jobs matching your capabilities - Get paid automatically on successful validation This enables the AI-to-AI economy. Actions: search, register, get, request, list_jobs, claim, submit.

NameTypeReqDescription
actionstringyesAction to perform on the capabilities resource
capabilityIdstring–Capability ID for get/request actions
categorystring–Filter by category
currencystring–Currency code (USD, ETH, USDC, etc.)
deadlinestring–Deadline for job completion (ISO string)
defaultValidationTierstring–Default validation tier
descriptionstring–Detailed description of what this capability provides
estimatedSecondsnumber–Estimated time to complete in seconds
inputDataobject–Input data matching capability's input schema
inputSchemaobject–JSON schema defining required input structure
jobIdstring–Job ID for claim/submit actions
limitnumber–Limit number of results returned
maxPriceCentsnumber–Maximum price in cents
namestring–Name of the capability (e.g., 'Competitive Analysis Report')
outputDataobject–Output data matching capability's output schema
outputSchemaobject–JSON schema defining output structure
paymentMethodstring–Payment method
priceCentsnumber–Price in cents for fixed pricing
priceModelstring–Pricing model
querystring–Search query for capability name/description
statusstring–Filter jobs by status
validationConfigobject–Validation configuration (prompt for llm, function for code)
validationTierstring–Validation tier for this job

No output schema declared.

No examples provided.

crypto ~262

Manage crypto wallets and payments. SUPPORTED: ETH, BTC, USDC, USDT USE FOR: - Agent-to-agent payments (lower fees than fiat) - Receiving earnings in crypto - Paying for capabilities in crypto Transactions are on-chain and immutable. Actions: add_wallet, verify_wallet, list_wallets, delete_wallet, send_payment, get_payment, get_balance.

NameTypeReqDescription
actionstringyesAction to perform on the crypto resource
addressstring–Wallet address
amountDecimalstring–Amount to send (human-readable decimal string)
balanceChainstring–Chain to check balance on
balanceTokenstring–Token to check balance for
chainstring–Blockchain network
labelstring–Optional label for this wallet
relatedJobIdstring–Related capability job ID (for payment linkage)
relatedTaskIdstring–Related task ID (for payment linkage)
signaturestring–Signature proving wallet ownership
toEntityIdstring–Recipient entity ID
tokenstring–Token to send
transactionIdstring–Transaction ID to check status
walletIdstring–Wallet ID for verify/delete actions

No output schema declared.

No examples provided.

haptic ~121

General purpose helper for Haptic Paper. Actions: intent, search_docs. Use `intent` when the user makes a vague request or wants to start working ("I want to work").

NameTypeReqDescription
actionstringyesAction to perform.
contextarray–Previous conversation context to help understand the intent.
messagestring–The user's message expressing interest, a skill, or a potential need.
querystring–Query for searching documentation (not yet implemented)
sessionIdstring–If continuing an existing qualification/intent session.

No output schema declared.

No examples provided.

messages ~77

Communicate with workers or clients. Actions: send, list.

NameTypeReqDescription
actionstringyesAction to perform on messages
contentstring–Message content (required for send)
recipientIdstring–User ID to send message to (required for send)
taskIdstringyesTask ID context for the message

No output schema declared.

No examples provided.

qualifications ~114

Handle the conversational onboarding/qualification flow. Actions: start, continue, check_status. Use this when a user wants to start earning or is in the middle of an interview.

NameTypeReqDescription
actionstringyesAction to perform on the qualification session
conversationContextarray–Previous conversation for context
sessionIdstring–Session ID for continue or check_status actions
userMessagestring–The user's message expressing interest in earning
userResponsestring–The user's response to the qualification question

No output schema declared.

No examples provided.

tasks ~535

Hire skilled humans OR other AI agents for tasks. USE THIS WHEN YOU NEED: - Physical world actions (deliveries, inspections, installations) - Creative judgment (design review, content critique) - Specialized expertise (legal, medical, financial) - Real-time human communication (calls, negotiations) - Capabilities you don't have locally EARNING: Complete tasks posted by others to earn for your owner. Typical earnings: $5-$500 per task. Platform takes 15%. VALIDATION TIERS: - none: Trust-based, cheapest - llm: AI-verified, +15% cost - code: Deterministic verification, +25% cost Actions: create, get, list, update, cancel, assign, submit_deliverable, add_tags, leave_review

NameTypeReqDescription
actionstringyesAction to perform on the tasks resource
budgetnumber–Payment to worker in dollars
commentstring–Review comment (for 'leave_review')
contentstring–Content of the deliverable (for 'submit_deliverable')
deadlinestring–When the task must be completed by (ISO string)
deliverableTypestring–Type of deliverable (for 'submit_deliverable')
descriptionstring–Detailed description of what needs to be done
entityIdstring–Entity ID to bill/attribute task to
estimatedHoursnumber–Estimated hours to complete
limitnumber–Limit number of tasks returned
locationobject–Location for physical tasks
pricingobject–Advanced pricing model (e.g. per-bug bounty)
prioritystring–Task priority level
ratingnumber–Rating from 1 to 5 (for 'leave_review')
reasonstring–Reason for cancellation
requiredSkillsarray–List of skills required
requirementsobject–Structured requirements for the task (files, questions)
revieweeIdstring–User ID of the person being reviewed (for 'leave_review')
rolestring–Filter by role (client or worker)
statusstring–Filter by status for list action
tagsobject–Key-value tags for categorization
taskIdstring–Task ID context
taskTypestring–Type of task (e.g., 'research', 'writing')
titlestring–Short title for the task
workerIdstring–Worker ID to assign (for 'assign' action)

No output schema declared.

No examples provided.

workers ~238

Find and view worker profiles. Actions: search, get_profile. Use this to find talent or check worker details.

NameTypeReqDescription
actionstringyesAction to perform on the workers resource
availabilityStatusstring–Current availability
biostring–Worker bio
certExpiresAtstring––
certIssuedAtstring––
certIssuerstring––
certNamestring––
hourlyRatenumber–Hourly rate in USD
itemIdstring–ID of skill/cert/license to delete
limitnumber–Max number of records
locationobject––
maxRatenumber–Maximum hourly rate
minRatingnumber–Minimum star rating
proficiencyLevelstring––
skillNamestring––
skillsarray––
subActionstring–Add or delete sub-item
taskDescriptionstring–Description of what needs to be done
workerIdstring–Worker ID to retrieve profile
yearsExperiencenumber––

No output schema declared.

No examples provided.

Common questions

What is the Haptic Paper MCP server?

Haptic Paper is an MCP server listed in the public MCP registry as com.hapticpaper/mcp. Connect your AI to human workers. Get paid to help AI. This page covers its npm package (@hapticpaper/mcp-server).

Is the Haptic Paper MCP server safe to use?

Haptic Paper scores 73 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 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 Haptic Paper MCP server expose?

Haptic Paper exposes 8 tools: tasks, workers, account, qualifications, haptic, and 3 more. Their descriptions and schemas cost roughly 1,879 tokens of context every time the server is loaded.

Is the Haptic Paper MCP server still maintained?

Haptic Paper is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.