Phala Network MCP Server (Tairon-ai/phala-mcp) is an MCP server listed on the M8ven Trust Index. It scores 56 out of 100, grade D. It declares 31 tools. No publisher has claimed this listing.
Enables interaction with Phala Network's confidential computing infrastructure, including TEE worker management, AI agent deployment in secure enclaves, and blockchain operations.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
Tairon-ai
Source: Glama
Operator-pattern signals come from machine analysis of every MCP under this publisher's GitHub org. They are factual aggregates — not accusations. Investigate the individual MCPs before drawing conclusions.
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
getServiceInfoGet information about the Phala MCP service and capabilities
getChainInfoGet current Phala Network chain information and statistics
getPHABalanceGet PHA token balance for an address
sendPHASend PHA tokens to another address
getWorkerListGet list of TEE workers on Phala Network with their status
getWorkerInfoGet detailed information about a specific TEE worker
verifyAttestationVerify TEE attestation report for a worker
getPhatContractListGet list of deployed Phat Contracts with their metadata
deployPhatContractDeploy a new Phat Contract to a cluster
queryPhatContractQuery a Phat Contract (read-only, no gas required)
executePhatContractExecute a Phat Contract method (state-changing, requires gas)
deployAIAgentDeploy an AI Agent contract with TEE protection
queryAIAgentSend a query to an AI Agent running in TEE
deployContainerDeploy a Docker container in TEE using DStack
getContainerStatusGet status of a deployed container
getClusterInfoGet information about compute clusters
createClusterCreate a new compute cluster
getStakingInfoGet staking pool information and delegation details
delegateStakeDelegate PHA tokens to a staking pool
getPHABalanceEthereumGet PHA token balance on Ethereum mainnet
sendPHAEthereumSend PHA tokens on Ethereum mainnet
getPHABalanceCrossChainGet PHA token balance across both Phala Network and Ethereum
getPHATokenInfoGet PHA token information on Ethereum
generateVRFGenerate verifiable random number with proof
fetchOracleDataFetch external data through blockchain oracle
createWorkflowCreate automated workflow with triggers and actions
getAIAgentTemplatesGet pre-configured AI agent templates
deployAIAgentTemplateDeploy an AI agent using a pre-configured template
sequentialThinkingBreak complex tasks into sequential steps
fetchRealtimeDataFetch real-time data from various sources
personalFinanceManage personal finance operations
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`
axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollution Gadget in Config Merge
AI_AGENT_FACTORY_ADDRESSATTESTATION_SERVICE_URLDSTACK_API_URLDSTACK_REGISTRY_ADDRESSDSTACK_REGISTRY_URLETHEREUM_RPC_URLORACLE_ENDPOINTPHALA_API_KEYPHALA_PHAT_RPC_URLPHALA_RPC_URLPHAT_FACTORY_ADDRESSTEE_WORKER_ENDPOINTVRF_ENDPOINTWALLET_PRIVATE_KEYWALLET_SEED_PHRASEPORTTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
31/31 tools missing one or more hints — getServiceInfo (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); getChainInfo (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); getPHABalance (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +28 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tests exist
No test files found
Add tests that exercise each declared tool.
Secrets not logged
6 secret values sent to log
Redact or omit secret values from log output.
Production dependencies are patched
0 critical, 15 high severity in production deps — @modelcontextprotocol/sdk@1.17.5 (high), @modelcontextprotocol/sdk@1.17.5 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/tairon-ai/phala-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check