TDM MCP Server
OfficialClick on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@TDM MCP Servercheck session state and recommend next action"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
TDM MCP Server
Model Context Protocol Server for TDM
Session-state checks for AI agents
Documentation • Quick Start • GitHub • X/Twitter
What is TDM MCP Server?
@tdm/mcp-server is a small MCP stdio server for TDM local session-state checks.
The public GitHub repo for tdm-sdk shows the open contract-facing SDK
surface: https://github.com/ToDealMarket/tdm-sdk
The current tdm-sdk npm beta used by the surrounding TDM docs remains
broader and includes the CLI/operator flows referenced here.
Inside the broader Integration Kit, this package is the reference MCP implementation. It sits next to:
thin CLI and signer wrappers
copy-paste framework examples
lightweight local integration recipes
████████╗ ██████╗ ███╗ ███╗
╚══██╔══╝ ██╔══██╗ ████╗ ████║
██║ ██║ ██║ ██╔████╔██║
██║ ██║ ██║ ██║╚██╔╝██║
██║ ██████╔╝ ██║ ╚═╝ ██║
╚═╝ ╚═════╝ ╚═╝ ╚═╝
TDM CLI [V0.0.2-BETA]
SDK + CLI + MCP
Mode: local-first | Docs: todealmarket.com/docsRelated MCP server: Privy MCP Server
What it helps with
The tool helps an agent decide whether it should:
continue
ask the user to run
tdm connectsuggest
tdm fuelsuggest
tdm sweep
Interactive seller commands in tdm-sdk can now auto-start that one-time
Live TDM setup when the live runtime is still missing. MCP still keeps the
explicit instruction path because an agent should ask the operator before
triggering wallet/browser setup on their behalf.
For human operator flows, tdm connect stores the primary wallet locally.
The current multi-wallet MVP also supports connecting one wallet per supported
network for local signing and network-specific payout setup. During connect,
TDM can attempt a safe default payout sync for the same network when that
network does not already have a saved payout wallet. It does not overwrite an
already saved payout wallet automatically, and
tdm connect --no-sync-payout-wallet keeps connect local-only.
If the account protects new payout destinations with TOTP step-up, the operator should run:
tdm security totp enroll
tdm security totp verify --method-id <id> --code 123456tdm security totp enroll opens a local setup page with a QR by default. Use
--no-browser if terminal-only setup is preferred.
It is intentionally local-first:
reads local TDM credentials and runtime hints
follows
TDM_CREDENTIALS_PATHwhen explicitly setotherwise follows
TDM_VAULTor the active vault marker from~/.tdm/vaults/_activedoes not depend on deprecated treasury balance routes
can use
TDM_REMAINING_USDCandTDM_DUST_TOKENS_DETECTEDwhen the host wants to provide fresh snapshot hints
For operators using named vaults, MCP will read the active/default vault context instead of pretending there is only one global runtime forever.
The vault resolution order is explicit:
TDM_CREDENTIALS_PATHwhen you pin one credentials file directlyotherwise
TDM_VAULTotherwise the active vault marker from
~/.tdm/vaults/_activeotherwise the legacy default
~/.tdm/credentials.json
That means one MCP process reads one selected vault contour. It does not merge agents, wallets, or sessions across multiple vaults.
If that active vault has its own optional runtime allowlist, agents in that vault inherit the narrower destination policy. If no project or vault allowlist is configured, MCP keeps the broader flexible runtime posture instead of assuming deny-by-default.
If the operator wants reusable runtime contours, tdm workspace use <name>
can switch the active vault/storage combination before MCP starts. MCP still
reads local runtime state only; it does not own those runtime workspaces.
Local catalogs and published assets now live next to that same runtime layer in tdm-sdk:
tdm storage addtdm storage import-dirtdm storage synctdm storage watchtdm storage publishtdm workspacetdm statustdm workspace status
MCP itself does not host or upload those files. It can only help an agent or operator decide when to suggest the surrounding CLI workflow.
States
FUELEDDEPLETEDUNINITIALIZED
Representative response fields:
stateremaining_usdcwallet_linkeddust_tokens_detectedagent_instructionsbalance_source
Install
npm install @tdm/mcp-serverGlobal install:
npm install -g @tdm/mcp-serverIf you already use tdm-sdk, the simplest path is:
tdm mcpThat SDK command writes a project .mcp.json pointing to the bundled MCP runtime.
The standalone @tdm/mcp-server package itself does not mutate your project config files.
Run
tdm-mcp-serverBundled SDK path:
tdm mcp serveProgrammatic startup
import { startUltraThinRadarServer } from '@tdm/mcp-server';
await startUltraThinRadarServer();Example response
{
"state": "DEPLETED",
"remaining_usdc": 0,
"wallet_linked": true,
"dust_tokens_detected": true,
"agent_instructions": "Suggest tdm sweep.",
"balance_source": "runtime_snapshot"
}Scope
This package is a decision helper for agent runtimes. It is not a wallet manager, payout tool, or general execution framework.
If you need a live JavaScript gateway integration instead of local state
guidance, use tdm-sdk with makePayable(...), tdm-sdk/authorize,
tdm-sdk/checkout, tdm-sdk/session-tanks, or createGatewayClients(...).
If MCP suggests a recovery path such as tdm sweep, the current SDK routing
behavior behind that suggestion is:
Solana Jupiter:
https://api.jup.ag/swap/v1whenJUPITER_API_KEYis configuredhttps://lite-api.jup.ag/swap/v1as the compatibility fallback without a key
Base Odos:
https://api.odos.xyzwithoutODOS_API_KEYhttps://enterprise-api.odos.xyzwithODOS_API_KEY
The MCP server itself does not hold or manage those API keys; it only points
operators toward the surrounding tdm-sdk workflow.
If you need custom local signing for advanced third-party integrations, use the
experimental tdm signer serve mode from tdm-sdk instead of treating the MCP
server as a transaction executor.
Warning:
advanced users only
localhost-only signing surface
blind signing risk exists
TDM does not take responsibility for losses caused by compromised local scripts or unsafe third-party integrations in that mode
License
MIT
Available Tools
1 tooltdm_get_session_stateA
Provides the LLM Agent with local TDM balance snapshot hints and wallet status to determine whether x402 execution should continue or whether the user should run tdm connect, tdm fuel, or tdm sweep.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden of behavioral disclosure. It states that hints and status are provided, but does not specify whether the operation is read-only, what side effects exist, or the exact format of the output. The description is too vague about the actual behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that front-loads the core purpose. It is concise and avoids unnecessary words, though the phrasing 'local TDM balance snapshot hints' is slightly complex but still clear.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should explain what the tool returns. It mentions 'balance snapshot hints and wallet status' but does not detail the format or structure of the output, leaving gaps for the agent. The tool simplicity partially compensates, but more specificity is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and the input schema has 100% documentation coverage (empty). The description does not need to add parameter details, and it provides sufficient context for a parameterless tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool provides balance snapshot hints and wallet status to determine whether x402 execution should continue or alternative tools should be used. It names the specific resources and implies the decision-making purpose, but could be more direct about it being a 'get state' operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly suggests when to use this tool (before deciding on x402 execution) and mentions alternative tools (tdm connect, tdm fuel, tdm sweep). It lacks explicit 'when not to use' guidance, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
v0.1.0- First observed
tdm_get_session_state
TDQS
With only one tool, there is no possibility of confusion between tools; the single tool has a clear and distinct purpose.
The tool name follows a consistent verb_noun pattern with a server-specific prefix, which is clear and predictable.
A single tool is insufficient for the apparent domain, which involves multiple user actions (connect, fuel, sweep) that are not exposed as tools, making the surface feel incomplete and under-scoped.
The server only provides a state query tool but lacks any action tools for the operations it references (connect, fuel, sweep), leaving critical gaps that prevent an agent from completing workflows.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Provide AI agents and automation tools with contextual access to blockchain data including balance…
Verified memory for AI agents. Signed assertions, billing attestation, session continuity.
DeFi safety layer for AI agents: wallet safety, token risk, tx decode/simulate. 20 tools.
Pay-per-call safety checks for AI agents: screen a crypto address or URL before you transact.
Related MCP Servers
- AlicenseCqualityDmaintenanceEnables AI agents to interact with cryptocurrency ecosystems through wallet management, trading operations (swaps, DCA, limit orders), staking, and multi-chain support starting with Solana.37GPL 3.0

Privy MCP Serverofficial
AlicenseBqualityDmaintenanceEnables AI agents to create wallets, sign transactions, and manage blockchain operations across multiple chains like Ethereum, Solana, and more via Privy.242MIT- AlicenseAqualityDmaintenanceEnables AI agents to check balances and send transactions across multiple blockchains with automatic spending limit protection and policy enforcement.3MIT

Bink MCP Serverofficial
FlicenseNot gradedqualityDmaintenanceEnables AI agents to perform blockchain operations like wallet management, token info, DeFi swaps, cross-chain bridging, and price checking across Ethereum, BNB Chain, and Solana.-
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ToDealMarket/mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server