Tychi Wallet MCP gives your AI agent a self-custodial wallet on Arbitrum One, with local signing that never leaves your device. Key capabilities:
Intent routing (tyi_route): Maps agent intent to the correct tool first, preventing misuse of tyi_chat.
Readiness check (tyi_status): Inspects session state at startup before any wallet operations.
Onboarding (tyi_onboard + tyi_onboard_schema): First-time setup for keystore password, agent name, LLM provider (Anthropic, Gemini, OpenAI, or Groq), API key, and optional mnemonic import.
Wallet lifecycle: Create new wallets (tyi_create_wallet), import from BIP39 mnemonic or private key for EVM/Solana/Sui (tyi_import_wallet), and switch active wallet by name (tyi_switch_wallet).
Agent chat for financial ops (tyi_chat): Check balances, send/transfer funds, make policy-gated payments, query spend limits, and view transaction history — processed through the hosted Tychi brain LLM.
Secure local signing: Private keys are encrypted in ~/.tyi; signing never leaves the operator's machine.
Policy-enforced spending: Spend caps are checked before any transaction is signed.
Gasless payments: UGF payment rails handle gas settlement on Arbitrum One (chain id 42161).
Audit logging: Local activity trail maintained in ~/.tyi.
Data reset (tyi_reset): Wipes all local data in ~/.tyi when explicitly confirmed.
Enables AI agents to use OpenAI's LLM for wallet-related chat operations such as balance inquiries, transactions, and policy management.
Click 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., "@Tychi Wallet MCP what's my ETH balance on Arbitrum?"
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.
@tychilabs/tyi-mcp)
Give your AI agent a wallet — onboard, hold funds, send, and pay under policy.
Agent-native MCP server (stdio) for Cursor and other hosts. Nine tools: routing (tyi_route), readiness (tyi_status), onboarding, fast wallet lifecycle (create / import / switch), and tyi_chat for balances, sends, and policy-gated payments on Arbitrum One. Private keys encrypted in ~/.tyi on the operator machine; signing never leaves the device. Hosted Tychi brain parses intent and runs the LLM — configure TYCHI_BRAIN_URL (HTTPS recommended; see SECURITY.md).
Agents → @tychilabs/tyi-mcp@1.0.0-beta.8 · Humans → @tychilabs/tyi
Agent routing — tyi_route maps intent → correct tool (avoids slow misuse of tyi_chat)
Readiness gate — tyi_status checks mode before any wallet action
Onboarding — tyi_onboard + tyi_onboard_schema for first-time setup (password, LLM provider, API key)
Wallet lifecycle — tyi_create_wallet, tyi_import_wallet, tyi_switch_wallet (fast, no brain loop)
Agent chat — tyi_chat for balances, sends, transfers, payments, policy, limits, history
Multi-wallet — create, import, switch active wallet from one keystore
Policy caps — spend limits enforced before signing
Local signing — private keys in memory on operator machine only
Gasless routing — UGF payment rails for cross-chain gas settlement
Audit log — local activity trail in ~/.tyi
Reset — tyi_reset wipes local data when operator confirms
Beta ships on Arbitrum One (chain id 42161) — EVM balances, sends, and UGF gasless payments. More chains in registry; Solana/Sui import supported.
Related MCP server: seashail
Onchain agent wallet on Arbitrum One — self-custody, local signing, UGF gas routing today:
Roadmap | What it unlocks |
Automation | Policy-gated agents — recurring sends, triggers, scheduled flows |
Trading | Spot swaps across Arbitrum liquidity — agent quotes, operator confirms |
Lending | Supply on Arbitrum money markets — yield without leaving keystore |
Borrowing | Collateralized borrow — cap-enforced, fully self-custodial |
tyi_route → tyi_status
→ direct tool (onboard / create / import / switch / reset) ← FAST
→ tyi_chat (balance / send / pay / policy only) ← SLOWNever call tyi_chat when tyi_status.ready is false.
Import seed or private key → tyi_import_wallet only (never via tyi_chat).
Tool | Use when |
| First — intent → tool map |
| Session start — ready? what's missing? |
| Field schema before onboard |
| First setup or LLM-only setup |
| New wallet by name |
| Import mnemonic or privkey (EVM / Solana / Sui) |
| Change active wallet |
| Wipe |
| Balance, send, pay, transfer, policy, limits |
Pin the release (do not use floating @beta in production):
npx @tychilabs/tyi-mcp@1.0.0-beta.8
npx @tychilabs/tyi-mcp@1.0.0-beta.8 --toolsSee SECURITY.md — trust model, brain transport (HTTP beta endpoint), sensitive tools, supply-chain pinning. No install scripts.
Repo includes .mcp.json (Open Plugins) for Cursor Directory. Set TYI_PASSWORD and TYCHI_BRAIN_URL in host env (HTTPS brain recommended).
{
"mcpServers": {
"tychi": {
"command": "npx",
"args": ["@tychilabs/tyi-mcp@1.0.0-beta.8"],
"env": {
"TYI_PASSWORD": "<from tyi_onboard>",
"TYCHI_BRAIN_URL": "<https brain URL — required>"
}
}
}
}Beta default if unset in code: http://hosted_brain.tychilabs.com — use HTTPS self-host or trusted network only.
OpenClaw:
openclaw mcp set tychi '{"command":"npx","args":["@tychilabs/tyi-mcp@1.0.0-beta.8"],"env":{"TYI_PASSWORD":"<password>","TYCHI_BRAIN_URL":"<https brain URL>"}}'
openclaw mcp reloadMode | Meaning |
| No wallet — run |
| Wallet exists, no LLM key — onboard LLM fields only |
| OK for |
Operator provides (never invent): keystore password, LLM provider + API key, optional mnemonic for import.
Prefer MCP env for TYI_PASSWORD over chat after onboard.
Field | Prompt |
| Keystore password for |
| Agent name (default |
|
|
| Provider API key (validated, stored encrypted on brain) |
| Optional import (fresh only) |
tyi_reset with { "confirm": true } — wipes ~/.tyi
Remove TYI_PASSWORD from MCP env
OpenClaw: openclaw mcp unset tychi then openclaw mcp reload
Symptom | Action |
| Run onboard flow |
| Set env after onboard; reload host |
|
|
|
|
| Set |
Variable | Required | Default |
| After onboard | — |
| Recommended |
|
| No |
|
| Alias | same as |
Website: https://tychilabs.com
Human CLI: https://www.npmjs.com/package/@tychilabs/tyi
Apache License 2.0 — see LICENSE. Runtime dependency: @tychilabs/tyi.
SLOW brain agent. ONLY: balance, send, pay, transfer, policy, limits, history, general Q. NEVER: create wallet, import, onboard, reset, switch — use dedicated tyi_* tools instead.
| Name | Required | Description | Default |
|---|---|---|---|
| message | Yes | Balance, send, pay, policy — not create/import/onboard | |
| reset | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description notes the tool is 'SLOW', which is a useful behavioral hint, but with no annotations, it fails to disclose other aspects like response format, error behavior, or rate limits. It covers the most critical aspect for a chat tool (slowness) but lacks broader context.
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 extremely concise (two sentences), front-loads the key caveat ('SLOW'), and every word adds value. No redundancy.
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 the tool's simplicity (two params, no output schema), the description covers scope, exclusions, and a behavioral warning. It does not explain the return value or the reset parameter's effect, but for a chat tool the output is implied.
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 description adds value beyond the schema by specifying allowed topics for the message parameter ('Balance, send, pay, policy'), which is not present in the schema's bare description. The reset parameter lacks detail, but the higher coverage of the main parameter compensates.
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 uses a specific verb ('SLOW brain agent') and explicitly lists the allowed operations (balance, send, pay, etc.) and prohibited ones, clearly distinguishing from sibling tools like tyi_create_wallet.
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 states when to use (for the listed topics) and when not to use (create, import, onboard, etc.), providing direct alternatives ('use dedicated tyi_* tools instead').
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
FAST. New wallet by name. User said create/new wallet → call this NOT tyi_chat.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | New wallet name | |
| label | No | Display label |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only adds 'FAST' as a performance hint but omits behavioral traits like what happens on duplicate wallet names, required permissions, or side effects. The description lacks essential behavioral context for a creation action.
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 extremely concise at two sentences, front-loading the key message 'FAST. New wallet by name.' Every word earns its place, with no redundant or tangential information.
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 and no annotations, the description should explain return values and error behavior. It does not address what the tool returns (e.g., wallet object or ID) or handle edge cases. It is adequate for simple use but lacks completeness.
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?
Schema coverage is 100% with both parameters described. The description adds 'by name' emphasizing name as key but provides no additional syntax or format guidance. Baseline 3 is appropriate as the schema already documents meaning.
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 'New wallet by name' and provides an explicit usage rule: 'User said create/new wallet → call this NOT tyi_chat.' This distinguishes it from sibling tool tyi_chat, making the purpose specific and actionable.
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 gives explicit guidance on when to use this tool vs tyi_chat. However, it does not address other siblings like tyi_import_wallet or provide when-not-to-use scenarios beyond the single distinction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
FAST. Import seed/privkey. User said import/restore → call this NOT tyi_chat. Secret via tool param only.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | New wallet name | |
| kind | Yes | ||
| secret | Yes | Seed or private key — operator only, never tyi_chat | |
| label | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries burden. It mentions 'FAST' and security ('operator only'), but lacks disclosure of side effects, preconditions, or error handling. Moderate transparency.
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?
Very short, two sentences plus a note. No wasted words, but 'FAST' is somewhat extraneous. Efficient overall.
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?
No output schema, no annotations, and description omits return values, error cases, prerequisites (e.g., user authentication). For an import tool, this is insufficiently complete.
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?
Schema coverage is 50% (name and secret have descriptions). Description adds context that secret is sensitive and must not go through tyi_chat, but does not explain 'kind' or 'label' beyond schema. Partial value added.
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?
Description clearly states 'Import seed/privkey' and specifically directs when user says 'import/restore' to use this tool over tyi_chat. Verb+resource is explicit.
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?
Explicitly says 'User said import/restore → call this NOT tyi_chat', providing a clear when-to-use and an alternative. Also notes 'Secret via tool param only' for security.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
FAST. First-time setup only. NOT tyi_chat.
| Name | Required | Description | Default |
|---|---|---|---|
| password | Yes | Keystore password (operator-provided) | |
| llm_provider | Yes | ||
| llm_api_key | Yes | Provider API key | |
| agent_name | No | ||
| mnemonic | No | Optional BIP39 import (fresh only) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions 'FAST' but does not disclose behavioral traits such as authentication requirements, side effects (e.g., overwriting existing data), or rate limits. The tool likely creates or initializes a wallet, but this is not explicit.
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 very short (three fragments), front-loading key information ('FAST. First-time setup only. NOT tyi_chat.'). Every word adds value, though it could benefit from a slightly expanded structure.
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 5 parameters, no output schema, and no annotations, the description is severely incomplete. It fails to explain what 'onboard' means, the purpose of the mnemonic and agent_name parameters, or the outcome of the operation.
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?
Schema coverage is 60% (three of five parameters have descriptions), but the tool description adds no parameter information. The description consists only of fragments about usage, leaving parameter meaning entirely to the schema. For a tool with 5 parameters, this is insufficient.
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 states 'First-time setup only' and 'NOT tyi_chat', clearly indicating the tool is for initial onboarding and not for chat. This distinguishes it from the sibling tool tyi_chat, though the specific verb 'onboard' is not explicit.
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 says 'First-time setup only' (when to use) and 'NOT tyi_chat' (when not to use), providing clear usage context and excluding a sibling tool. However, it does not mention alternatives for subsequent setups.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Onboarding field schema. Use with tyi_onboard — not tyi_chat.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose any behavioral traits such as whether the tool is read-only, has side effects, or requires authentication. The description carries the full burden but fails to provide any behavioral context.
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 extremely concise, using a single sentence and a dash-separated note. It is front-loaded with the core purpose.
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 the absence of an output schema and annotations, the description adequately conveys the tool's purpose but does not explain the return format or schema structure. It meets minimal viability for a simple tool with no parameters.
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?
There are zero parameters and 100% schema coverage. The description does not need to add parameter information, so baseline score of 4 is appropriate.
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 identifies the tool as an onboarding field schema and distinguishes it from tyi_chat, but it does not use a specific verb to describe an action (e.g., 'retrieves' or 'defines').
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 states to use with tyi_onboard and not tyi_chat, providing clear context for when to use. It does not list other alternatives or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Wipe ~/.tyi. confirm:true required. NOT tyi_chat.
| Name | Required | Description | Default |
|---|---|---|---|
| confirm | Yes | Must be true |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries the burden. It clearly indicates a destructive action ('Wipe') and mandates a confirm parameter, implying irreversibility. However, it lacks details about what exactly gets wiped (e.g., all data, config, etc.) or any side effects.
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 very concise, using three short statements. It is front-loaded with the primary action. However, it lacks full sentences and could be slightly more structured for readability.
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 the tool's simplicity (one parameter, no output schema), the description covers the essential action and the required confirmation. However, it does not explain the full scope of the wipe operation or any potential consequences, leaving some ambiguity.
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?
Schema coverage is 100% with the boolean parameter 'confirm' described as 'Must be true'. The description repeats this ('confirm:true required'), adding no new information beyond what the schema already provides.
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 'Wipe ~/.tyi' clearly states the action (wipe) and the resource (~/.tyi). The additional 'NOT tyi_chat' helps differentiate this tool from a sibling, making the purpose unambiguous.
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 mentions 'confirm:true required' which specifies a necessary usage condition, but it does not provide explicit guidance on when to use this tool versus alternatives like tyi_chat or other siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
READ FIRST. Intent → tool map. Call before any wallet op. Prevents slow tyi_chat misuse.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavior. It states it's a routing/mapping tool but does not describe side effects, data retrieval, or whether it modifies state.
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?
Two short sentences, front-loaded with 'READ FIRST', no wasted words.
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?
The tool has no output schema, so the description should explain what it returns. It does not describe the output format or structure, which is a gap for completeness.
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?
No parameters, baseline 4. The description does not add parameter information, but none is needed.
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 the tool is an 'Intent → tool map' and should be called before any wallet operation, distinguishing it from siblings like tyi_chat.
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?
Explicitly instructs to 'Call before any wallet op' and 'READ FIRST', and mentions it prevents slow tyi_chat misuse, providing clear context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check ready + missing. Call once at session start.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description implies a read-only operation but does not explicitly state it is non-destructive or safe. With no annotations, this is adequate but not fully transparent.
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?
Two sentences, no wasted words, front-loaded with purpose. Highly efficient.
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?
For a tool with no output schema, the description does not explain return values or what 'ready' and 'missing' mean. Lacks completeness on output behavior, though simple.
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?
No parameters exist; schema coverage is 100%. The description need not add param info, meeting the baseline for zero-parameter tools.
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 the tool checks 'ready + missing' status and is to be called at session start. It differentiates itself from sibling tools like tyi_chat or tyi_create_wallet by being a status check.
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?
Explicitly says 'Call once at session start', providing clear usage context. Does not specify when not to use or alternatives, but this is sufficient given the tool's niche.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
FAST. Set active wallet by name. NOT tyi_chat.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Wallet name to activate |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It implies a mutation (setting active wallet) but does not disclose side effects, permissions, speed context beyond 'FAST', or any error conditions.
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 extremely concise with only two fragments: 'FAST. Set active wallet by name. NOT tyi_chat.' Every word adds value, and the most critical info (speed and sibling relationship) is front-loaded.
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?
For a simple tool with one parameter, no output schema, and no nested objects, the description covers the essential action and differentiation. However, it lacks behavioral context (e.g., what happens on failure) and assumes knowledge about 'tyi_chat'.
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?
Schema coverage is 100%, with parameter 'name' described as 'Wallet name to activate'. The description adds 'FAST' and sibling info but does not enhance parameter understanding beyond schema. Baseline 3 applies.
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 the tool's purpose: 'Set active wallet by name.' It explicitly distinguishes itself from sibling tool 'tyi_chat' with 'NOT tyi_chat.', ensuring unambiguous purpose.
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 provides minimal guidance: 'FAST' suggests it's efficient, and 'NOT tyi_chat' warns against misuse. However, it lacks explicit when-to-use conditions, prerequisites, or alternatives beyond the sibling distinction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool has a clearly distinct purpose, with explicit instructions on when to use each and when NOT to use tyi_chat. The tyi_route tool further aids in disambiguation by mapping intents to tools.
All tools follow a consistent tyi_ prefix with snake_case naming. Most use a verb_noun pattern (e.g., tyi_create_wallet, tyi_import_wallet), with a few noun-only names (tyi_chat, tyi_status, tyi_route) that are still predictable and uniform.
9 tools is well-scoped for a wallet management server. Each tool serves a distinct function (onboarding, wallet creation/import/switch, reset, status, chat, routing), and there is no redundancy or unnecessary bloat.
The tool surface covers core wallet operations: onboarding, creation, import, switch, reset, status, and general queries via chat. While transactional actions like send/pay are handled through tyi_chat rather than dedicated tools, the surface is still complete for the domain.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for Gainium — manage trading bots, deals, and balances via AI assistants
Hosted MCP server for live Bittensor chain reads and self-custodial on-chain writes.
MCP server for Boson Protocol — on-chain agentic commerce for physical & digital goods.
Tenzro Network MCP server: wallet, identity, payments, inference, staking, bridges, verification.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/TychiWallet/tyi-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
