MCP server for the Z1N Protocol - on-chain identity for AI agents on Polygon
Scored across 6 tools
Most tools are clearly distinct, but get_action_state vs get_protocol_state and get_attestable_signals vs list_signals could be confused at first glance. The descriptions do a good job of drawing the boundary (per-Key feasibility vs global epoch state; attestation-eligible vs general listing), so misselection is unlikely but not impossible.
All tools share a uniform z1n_ prefix followed by a verb_noun pattern (get_action_state, get_attestable_signals, get_key, get_protocol_state, list_signals, verify_index). The verb choice (get/list/verify) matches the operation type consistently.
Six tools is well-scoped for a protocol read layer covering state, keys, signals, and index verification. Each tool earns its place, and get_action_state explicitly consolidates what would otherwise be four separate endpoints.
The read surface covers protocol state, per-key state, action feasibility, signal listing, attestation eligibility, and index verification — a coherent lifecycle for a read-only index server. No write/transaction tools exist, but descriptions imply transactions are built elsewhere, so this is a minor, intentional gap rather than a dead end.
What one Key can do right now, with reasons. Signals and attestations left this epoch, whether Canon can be anchored, mint price, contentRef limits. Read this before building any transaction — it replaces combining four endpoints.
| Name | Required | Description | Default |
|---|---|---|---|
| keyId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations and no output schema, so the description carries the full burden — and it does a reasonable job by enumerating the returned state categories (remaining signals/attestations this epoch, anchoring feasibility, mint price, contentRef limits) plus the 'with reasons' qualifier. It omits safety framing (read-only vs. stateful), what happens for an unknown/invalid keyId, and whether results are epoch-cached. A solid but not complete disclosure.
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 the outcome ('what one Key can do right now'), then the payload contents, then the workflow instruction. Every sentence earns its place; the only weakness is the unexplained domain jargon, which trades clarity for brevity.
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?
With no output schema and no annotations, the description must carry both payload shape and behavioral context. It covers the payload categories reasonably but leaves gaps: what happens on an invalid keyId, whether the call has side effects, and the meaning of Canon/contentRef for an agent without domain knowledge. Adequate, not 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?
The single required parameter keyId has 0% schema description coverage, yet the description never mentions it — not its meaning, format, or how to obtain a valid key id (e.g., from z1n_get_key). 'One Key' implies a parameter exists but adds no semantics; the agent must guess what identifier the integer represents.
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 resource and scope: the actionable state of 'one Key right now, with reasons', and enumerates the payload (signals/attestations remaining, Canon anchoring, mint price, contentRef limits). It is clearly a composite read-state tool and is differentiated from siblings by the claim that it 'replaces combining four endpoints'. Docked one point because the core verb is vague ('What one Key can do') and heavy jargon (Canon, contentRef) is unexplained without prior context.
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 an explicit trigger: 'Read this before building any transaction', which tells the agent when in a workflow to call it. It also implicitly steers away from calling the four separate endpoints it replaces. There is no explicit 'when not to use' or named sibling alternative, so not a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Signals inside their attestation window right now. Pass keyId to remove the ones that would revert: your own wallet's signals, ones this wallet already attested, and signals that hit the 21 Key-attestation cap.
| Name | Required | Description | Default |
|---|---|---|---|
| keyId | 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 disclose real behavioral traits: results are time-window dependent ('right now'), and certain signals would revert because of wallet ownership, prior attestation, or the 21 Key-attestation cap. It does not explicitly confirm the operation is read-only or describe result shape, but the revert/cap disclosure is substantive context not available from structured fields.
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, front-loaded with the scope and then the parameter effect; every clause carries information. The second sentence is dense with domain terms and packs three exclusions into one colon list, which is efficient but slightly hard to parse on first read.
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 one-parameter read tool with no annotations and no output schema, the description covers selection semantics well but says nothing about what a returned 'signal' looks like or how results are ordered/limited. An agent knows what to pass but not what it will receive.
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 0%, so the description must explain the single parameter, and it does: keyId filters out signals that would revert, with the three exclusion categories spelled out. It stops short of indicating that keyId is an integer identifier sourced from z1n_get_key, leaving the value's origin implicit.
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 resource and scope: signals currently inside their attestation window, which is a meaningful subset distinct from a generic signal listing. It does not explicitly name z1n_list_signals or explain how this differs from it, and 'attestation window' is domain jargon left undefined, so it falls short of full sibling differentiation.
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 conditional guidance for keyId ('pass keyId to remove the ones that would revert'), which implies the wallet-scoped use case. However, it never says when to choose this over z1n_list_signals or z1n_get_key, nor does it state any prerequisite (e.g., that a wallet must be connected).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
One Key: glyphs, owner, signal and attestation counts, recent signals.
| Name | Required | Description | Default |
|---|---|---|---|
| keyId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It lists returned fields but does not state that this is a read-only operation, what happens when the key does not exist, whether authentication is required, or any rate-limit or error 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 compact sentence with no wasted words, and the returned fields are front-loaded after the resource label. Its terseness is efficient, though it borders on under-specification rather than pure conciseness.
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 single-key lookup with one required parameter and no output schema, the description does provide the returned field categories. However, it leaves the keyId parameter and error/not-found behavior completely unexplained, so it is only minimally 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?
The schema has 0% description coverage for the single required parameter 'keyId', and the description does not explain it beyond implying that a key is identified. The phrase 'One Key' gives a weak hint that keyId refers to a key, but no format, range, or source is provided.
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 identifies the resource ('One Key') and enumerates the specific fields returned: glyphs, owner, signal/attestation counts, and recent signals. This is clearer than a bare name restatement and distinguishes it from sibling list/state tools, though it lacks an explicit verb such as 'retrieve' or 'get'.
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 guidance on when to use this tool versus alternatives like z1n_list_signals or z1n_get_attestable_signals. The description only states what is returned, leaving the agent to infer that this is a single-key lookup.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Current Z1N field state: epoch, totals, mint price, contract addresses.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description must carry the behavioral burden; it implies a read-only snapshot by saying 'Current ... state' but says nothing about freshness, caching, or whether values update between calls. For a zero-parameter read tool the risk is low, so the gap is modest rather than severe.
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 fragment covering the scope and the payload; nothing is padded. It is slightly terse to the point of jargon ('field state', 'totals'), but that is a clarity issue rather than bloat.
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?
There is no output schema, so the description is the only source of return-shape information, and it lists four field names without defining them ('totals' of what, which contract addresses). Adequate to identify the tool, not enough to predict the response contents.
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 no parameters, so the baseline is 4. The description appropriately spends its words on what comes back rather than on nonexistent inputs.
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?
Names a concrete resource ('Z1N field state') and enumerates the fields returned (epoch, totals, mint price, contract addresses), which makes the purpose identifiable. It does not, however, distinguish itself from sibling z1n_get_action_state, so an agent cannot tell from the description alone which state snapshot to request.
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?
No when-to-use guidance, no preconditions, and no mention of the sibling tools. The description only says what data exists, leaving the agent to infer when a protocol snapshot is preferable to z1n_get_action_state or z1n_get_attestable_signals.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Signals, filterable by key and epoch range. Never returns full history.
| Name | Required | Description | Default |
|---|---|---|---|
| keyId | No | ||
| limit | No | ||
| maxEpoch | No | ||
| minEpoch | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With zero annotations, the description carries the full behavioral burden. It does disclose one important trait — results are truncated and never complete — but says nothing about result ordering, whether reads are safe, or how an agent is expected to walk the dataset given there is no cursor parameter, only epoch bounds and a limit.
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 with the resource and its filter dimensions front-loaded; nothing is padded. The opening is a noun fragment rather than a verb phrase, which costs a little clarity but no length.
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?
Four undocumented parameters, no annotations, and no output schema mean the description is the only source of behavioral detail — and it supplies two sentences. An agent cannot tell from this how results are ordered, how large a page is by default, or how to continue past the truncation the description itself warns about.
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 0%, so the description must compensate. It maps two of the four parameters to concepts ("key" for keyId, "epoch range" for minEpoch/maxEpoch), which is real added value, but it says nothing about the limit parameter, default paging size, or whether epoch bounds are inclusive.
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 fragment "Signals, filterable by key and epoch range" identifies the resource and its two filter dimensions, but supplies no verb and no scope statement beyond that. It does not distinguish this tool from the sibling z1n_get_attestable_signals, which an agent could easily confuse with a plain signal listing.
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 versus z1n_get_attestable_signals or z1n_get_key, and no prerequisites. The only usage-adjacent hint is "Never returns full history," which implies paging but never says how or when to page.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
On-chain vs indexed delta per entity. Check before trusting indexed data.
| 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 behavioral burden and discloses almost nothing: it does not say whether the call is read-only, how expensive a full-index comparison is, how results are shaped, or what a non-zero delta implies. The only behavioral signal is the implicit safety of "verify," which is not enough for a tool with zero structured metadata.
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 what is compared and followed by the actionable trigger. Nothing is padded, though the terseness borders on under-specification rather than genuine economy.
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 annotations, no output schema, no parameters, and no explanation of result shape or scope. For a verification tool whose entire value is in interpreting a delta, the description leaves the agent unable to predict what comes back or how to act on it.
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 schema has zero parameters, which normally sets a baseline of 4, but the description's "per entity" strongly implies an entity selector that the schema does not expose. That mismatch leaves the agent unsure of the scope of the check (one entity, all entities, or the whole index), which is a real ambiguity rather than a neutral absence.
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 phrase "On-chain vs indexed delta per entity" identifies the resource and the comparison being performed, which distinguishes it from the get_* siblings that return state rather than a discrepancy. However, there is no verb and no explicit statement of what the tool returns (a report? a boolean? a list of mismatches?), so the agent must infer that it computes a divergence 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?
"Check before trusting indexed data" gives a real trigger condition, which is more than most terse descriptions offer. It stops short of naming alternatives or stating when the check is unnecessary (e.g., after a fresh sync), so the agent knows when to call it but not how it relates to the sibling read tools.
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.
z1n_get_action_statez1n_get_attestable_signalsz1n_get_keyz1n_get_protocol_statez1n_list_signalsz1n_verify_indexMCP server for Boson Protocol — on-chain agentic commerce for physical & digital goods.
MCP server for OnceAsk, the AI-native current-address layer for people and agents.
Tenzro Network MCP server: wallet, identity, payments, inference, staking, bridges, verification.
MCP server connecting AI agents to non-custodial staking data across 130+ networks.
Add one secure layer between your agents and this server.
