Solana token rug checks and safety-checked Jupiter swaps for AI agents; paid data via x402.
Scored across 3 tools
Each tool targets a distinct action: listing paid data endpoints, building a safety-checked swap, and checking token safety. The overlap in safety logic between token_check and safe_swap is inherent but clearly separated by their described purposes, preventing misselection.
All tools use the 'mosn_' prefix and snake_case, maintaining a consistent style. However, the naming pattern is not a strict verb_noun convention (e.g., paid_endpoints is adjective_noun), which is a minor deviation from the ideal.
Three tools fall well within the typical 3-15 range. Each tool serves a distinct, non-redundant purpose, making the set well-scoped and efficient for the server's focus.
Core safety operations (token check and safe swap) are covered. The paid endpoints tool only lists external endpoints rather than invoking them, and no batch or wallet-level checks exist, leaving minor gaps that an agent can work around.
List MOSN paid data endpoints (x402, USDC on Solana or Base): fresh screened Solana alpha, real-time new pools, holder checks, labeled memecoin dataset.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It does disclose the payment model (x402, USDC on Solana or Base), which is genuine behavioral context beyond the name. However, it never says whether calling this listing tool itself costs money or requires auth, nor does it mention rate limits or pagination.
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?
A single front-loaded sentence with no wasted clauses; the resource comes first and the category enumeration is compact. Nothing in it is redundant with structured fields.
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 zero-param, no-annotation, no-output-schema tool the description is adequate on purpose but thin on behavior: it does not say whether the call is free, what an endpoint record contains, or how results are ordered/paged. An agent knows what the tool lists but not what it gets back.
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 takes zero parameters, so per the baseline the schema cannot be improved on by prose and a 4 applies. The description correctly adds no parameter discussion, matching the empty input schema.
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?
States a specific verb (List) plus the resource (MOSN paid data endpoints) and enumerates the categories returned: screened Solana alpha, new pools, holder checks, labeled memecoin dataset. It is clearly distinguishable from siblings mosn_safe_swap and mosn_token_check, though it never names them explicitly.
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?
There is no statement of when to use this tool versus the alternatives, nor any prerequisites (e.g. 'call this first to discover endpoints, then use mosn_safe_swap'). The agent must infer that this is a discovery/catalog tool purely from the word 'List'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Build a Solana token swap that is safety-checked first: MOSN refuses buys into DANGER tokens, then returns an unsigned Jupiter swap transaction for YOUR wallet to sign (MOSN takes a 0.3% platform fee). Free to call.
| Name | Required | Description | Default |
|---|---|---|---|
| mint | Yes | ||
| side | Yes | ||
| wallet | Yes | Your Solana wallet public key | |
| amountRaw | No | For sells: token amount in base units | |
| amountSol | No | For buys: SOL to spend | |
| slippageBps | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses the safety gate, that the returned transaction is unsigned and must be signed by the caller's own wallet (non-custodial), the 0.3% platform fee, and that calling is free. It omits slippage defaults and what actually happens on a refused DANGER buy (error vs. partial result).
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?
A single dense sentence that front-loads the safety-check behavior, then the return contract, the fee, and the cost. Nothing is redundant or padded.
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 exists, but the description does explain the return value (an unsigned Jupiter swap transaction for the caller to sign). For a 6-param mutation tool it is nearly complete; slippage defaults and the failure mode for refused buys are the remaining gaps.
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 description coverage is 50%, so half the parameters (mint, side, slippageBps) rely on the description. The buy/sell asymmetry is hinted at via the DANGER-buy rule, but no format, unit, or default guidance is added for slippageBps or the mutually exclusive amountRaw/amountSol fields beyond what the schema already says.
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?
States a specific verb and resource ('Build a Solana token swap') plus the distinguishing safety gate ('MOSN refuses buys into DANGER tokens'). It is clearly separable from mosn_token_check, though it never names a sibling explicitly.
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?
Usage is implied rather than stated: the description tells the agent a swap is safety-checked and that buys into DANGER tokens are refused, but it never says when to pick this over mosn_token_check or mosn_paid_endpoints, and no prerequisites (wallet funding, token-account existence) are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Rug/safety check for a Solana token: mint & freeze authority, dangerous Token-2022 settings, real-wallet holder concentration (pools excluded), live sell-route test. Returns SAFE/CAUTION/DANGER with reasons. 5 free checks per day, then use the paid x402 endpoint.
| Name | Required | Description | Default |
|---|---|---|---|
| mint | Yes | Solana token mint address |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses the return contract (SAFE/CAUTION/DANGER with reasons), the rate limit (5 free checks/day), and the paid fallback. It stops short of stating that the live sell-route test makes real network calls (latency/timeout behavior) or whether any auth/API key is needed for the free tier.
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?
Three dense sentences, front-loaded with purpose, then checks, then verdict format and quota. Every clause conveys distinct information with no filler.
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 single-parameter tool with no output schema or annotations, the description covers the verdict format, the checks performed, and the quota/pricing model, which is what an agent needs to call and interpret it. Minor gaps remain around latency from the live sell-route test and any auth requirements.
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?
Only one parameter and schema description coverage is 100%, so the schema already documents 'mint' as a Solana token mint address. The description adds no format, network, or validation detail beyond what the schema provides, so the baseline of 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?
States a specific verb+resource ('Rug/safety check for a Solana token') and enumerates exactly what is inspected: mint & freeze authority, Token-2022 settings, real-wallet holder concentration, live sell-route test. An agent can distinguish this from mosn_safe_swap (swapping) and mosn_paid_endpoints (payment/endpoint listing) without opening any schema.
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?
Gives a concrete usage constraint and routing rule: '5 free checks per day, then use the paid x402 endpoint,' which names an alternative path. It does not, however, state when this check should be run versus the sibling tools (e.g., before a swap via mosn_safe_swap), leaving the sibling-selection decision implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
mosn_paid_endpointsmosn_safe_swapmosn_token_checkPre-trade token safety checks for AI agents on Solana and Base. x402 USDC per call, no key.
Solana token safety for AI agents — rug-pull, honeypot & Token-2022 trap detection before you buy.
x402 paid API tools for AI agents on Solana: crypto safety, market data, KYB/AML verification.
Safe Solana swaps for AI agents with risk checks, unsigned transactions, x402, and 3-bp fees.
Add one secure layer between your agents and this server.