Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Read NablaZ's open record: agent actions under permission, cited onchain. Evidence, not a verdict.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://read.nablaz.io/mcpRun this in your terminal
claude mcp add --transport http reader https://read.nablaz.io/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"reader": {
"url": "https://read.nablaz.io/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"reader": {
"type": "http",
"url": "https://read.nablaz.io/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://read.nablaz.io/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 6, 2026. The maker wrote them, not us; we show them as plain text.
read_subjectReturns every fact the reader has indexed about an address on one chain, as GET /read/:chainId/:address JSON: each fact names its source, carries a permission label of shape (a) to (e), and cites the block, transaction and log index with a command that returns the same log from a
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified against the domain nablaz.io (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 121 ms (HTTP 200)
No sign-in needed
Read 1 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (0.1.0) reached the registry today.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, Python MCP
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Local-only Python MCP server for the Files.com API.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
An open-source reader for agent payment permissions. It rebuilds, from public chain data, what an address was allowed to spend, what it spent, and under which terms, and keeps every fact next to the command that reproduces it. It reads the NablaZ record and grantee vaults, Coinbase spend permissions, MetaMask delegations and Agent Credit Lines.
It holds no keys, needs no account or API key, and runs anywhere you have an RPC endpoint.
Arbitrum One and Base are both enabled. The NablaZ contracts are live on Arbitrum One only, so on Base the reader indexes the third-party sources alone.
Third-party sources, on both chains:
SpendPermissionManager: SpendPermissionApproved, SpendPermissionUsed, SpendPermissionRevoked.DelegationManager (delegation framework v1.3.0): RedeemedDelegation, with every caveat decoded. For each redemption the reader reads the transaction receipt and keeps the ERC-20 Transfers sent by the delegator. A redemption alone is not a payment; only such a Transfer is.Borrowed, Repaid, Defaulted) at a configured lender. No lender is known on either chain today, so no lender is registered. The decoder ships with tests, and a read with nothing indexed says "nothing indexed" with its block range.NewFeedback from the "Reputation Registry" (who rated which agentId, and where; never the feedback's value, decimals, tags, endpoint or URIs), and the agentWallet and owner histories from the Identity Registry's MetadataSet and ERC-721 Transfer. Addresses from src/generated/erc8004.json (vendor commit pinned there).NablaZ sources, where deployed:
RecordEntry from NablaRecord, every field.AccountCreated from NablaAccountFactoryPermanent and AccountRegistryV6, to discover accounts.Upgraded on every discovered account proxy.AuthorizationUsed and Transfer where the authorizer or sender is a grantee vault. Vaults are discovered from logs alone: the PAY_AUTHORIZED entry names the vault, and the funding Transfer in the same transaction confirms it.| Table | One row per |
|---|---|
record_entries | RecordEntry, raw |
obligation_pairs | OBLIGATION_OPENED / REPAY / OBLIGATION_CLOSED entry, grouped by obligationRef |
vault_payments | settlement: a vault's AuthorizationUsed paired with its Transfer, and the grant and envelope it drew against |
implementation_history | Upgraded log or IMPLEMENTATION_CHANGED entry, per account |
counterparties | distinct (subject, counterparty) pair, with first evidence and counts |
accounts, grants, vaults, vault_fundings | discovery and pairing state the tables above are built from |
factory_accounts | account created on the permanent factory, with the owner from the factory's own event |
external_permissions | spend permission or redeemed delegation, with its shape, label and decoded terms |
external_payments | SpendPermissionUsed, or an ERC-20 Transfer from the delegator in a redemption's transaction |
external_redemptions | RedeemedDelegation, whether or not it moved value |
credit_line_events | Borrowed / Repaid / Defaulted at a configured lender |
feedbacks | ERC-8004 NewFeedback: agentId, rater, feedback index; no value, tags or URIs |
agent_wallets | ERC-8004 MetadataSet for the agentWallet key: agentId and wallet (null when cleared) |
agent_owners | ERC-8004 identity Transfer (ERC-721): agentId and new owner |
Rows hold facts and counts. The reader states facts and passes no judgement on any subject.
In vault_payments, the party that submitted the settlement transaction (tx.from) is recorded as submitter. It is never treated as the counterparty; the counterparty is the Transfer recipient.
A settlement writes no NablaRecord entry. A payment's record is two parts, paired by the reader: the PAY_AUTHORIZED entry the account wrote when it reserved funds into the grantee vault (the reservation, in record_entries), and USDC's own AuthorizationUsed and Transfer events (the settlement, one vault_payments row). A citation of a payment cites both: the PAY_AUTHORIZED log (block, transaction hash, log index) and the USDC settlement transaction and its block.
The logs are the ground truth; this reader is a convenience over them. Every row carries the chain id, block number, transaction hash and log index of its evidence, plus a cast logs command and the equivalent raw eth_getLogs request that return that log from any RPC. A row you cannot reproduce from its command is a bug.
One field is a state read, not a log: the envelope expiry in vault_payments. It is labelled "state read — needs archive RPC". The reader calls envelopeOf(account, granteeKey, token) on the account's mandate at block N−1 and at the settlement block N, and stores both calls as cast call --block commands. If the two reads agree, the value is stored. If they differ, the envelope changed within block N, and the field is stored as "not determinable" with both reads cited. On 2026-10-23, the same historical eth_call at 50,000 blocks below head answered 6 of 10 times through https://arb1.arbitrum.io/rpc, and the other 4 returned "historical state … is not available", so a public endpoint cannot be relied on for this field. Everything else rebuilds from logs on any RPC.
GET /read/:chainId/:address returns every indexed fact about an address. No key is needed: the endpoint is a read over public logs.
{ "subject": "0x…", "chainId": 8453, "asOfBlock": "53160200",
"facts": [ { "source": "metamask:delegation_payment", "label": "(b) exact execution, once", "shape": "b", "terms": { "payer": "0x…", "payee": "0x…", "token": "0x…", "amount": "…" }, "cite": { "chainId": 8453, "block": "…", "tx": "0x…", "logIndex": 0 }, "reproduce": "cast receipt 0x… --rpc-url \"$BASE_RPC_URL\" --json | jq …" } ], "selfDealing": null, "exposure": null, "cShare": { "chainId": 8453, "asOfBlock": "53160200", "byToken": { "0x…": { "count": { "c": 0, "total": 1 }, "value": { "c": "0", "total": "…" } } } }, "notes": [ "no Agent Credit Lines lender registered on this chain", "SpendPermissionManager permissions and spends for this address: nothing indexed (blocks 53160000..53160200)" ] }
Every permission label has one of five shapes:
| Shape | Label | Where it comes from |
|---|---|---|
| (a) | allowance, per period / total / per call / per execution / streamed | Coinbase spend permissions; MetaMask amount enforcers; NablaZ CAM V4 windows ("within mandate by construction" for a canonical NablaZ account) |
| (b) | exact execution, once / N times / count unbounded | MetaMask exact-call enforcers; the count from LimitedCallsEnforcer or a single-use enforcer |
| (c) | not determinable | an enforcer in no vendor list, terms that do not decode, a non-canonical NablaZ account |
| (d) | no limit on amount or call | a delegation whose caveats only restrict the call or the redeemer |
| (e) | third-party attestation, writer named | Agent Credit Lines; record entries another writer placed; ERC-8004 feedback, the rater named |
The MetaMask enforcer table is generated from the vendor's Deployments.md at a pinned commit (scripts/gen-enforcers.ts, src/generated/enforcers.json). A test fails when the vendor's main branch lists an enforcer the table lacks.
One-liners are the ground truth. The reader is a convenience over the logs. Each reproduce field is a cast command you can run yourself with an RPC URL in $ARB_ONE_RPC_URL or $BASE_RPC_URL.
When the subject has been the agentWallet or the owner of an ERC-8004 agentId, every NewFeedback about that agentId becomes an erc8004:feedback_grounding fact (R-D2B-2). A feedback is grounded when an ERC-20 Transfer from the rater to the identity's payment address settled before it (by block, then by log index within a block), whatever the token or route (R-S191-11). The payment address is resolved at the transfer's block, never later: getAgentWallet there, else ownerOf there, and the fact says which binding applied (R-S191-16). A transfer made before the identity existed does not ground ("identity did not exist at the payment block"). The wallet at the feedback block is reported beside the grounding ("wallet at feedback: " or "wallet at feedback: cleared") and is never the test (R-S191-12).
Plain transfers are not indexed. At read time the reader calls eth_getLogs with topic0 = Transfer and topic1 = the rater, any token address, from the Identity Registry's start block (or the instance's start) to the feedback block, and states that range in the fact. Candidates are the addresses in the identity's agentWallet history (MetadataSet) and owner history (ERC-721 Transfer), each confirmed at the transfer's block. A settlement from the rater's own grantee vault is a payment from the rater (R-S191-17). Native-token transfers are not read ("native-token transfers not read", R-S191-18). A transfer that is one of the reader's payment facts keeps its permission label; any other is labelled (c) with reason "direct transfer, no permission object". The fact also says whether the rater is the subject, and whether the two share a controller when both are NablaZ accounts. It carries no value, decimals, tags or URIs, and the feedback file is not fetched ("feedbackURI not read").
test/fork/afg.fork.test.ts runs this grounding on the 816 grounded feedback entries in Agentic Finance Graph's Base fixture (CC BY 4.0, see NOTICE) and writes the comparison to docs/reader/afg-agreement-2026-10-20.csv. docs/reader/retroactive-binding-2026-10.md describes the remaining disagreements.
https://read.nablaz.io runs the reader and the MCP server below as one instance, on both home chains (chain IDs 42161 and 8453), with every source indexed from its deployment block. It is keyless and reads only. It has two doors:
GET https://read.nablaz.io/read/:chainId/:address: the JSON a local GET /read returns.POST https://read.nablaz.io/mcp: the MCP server's Streamable HTTP transport, with its one tool, read_subject. For an MCP client that takes a URL: { "type": "http", "url": "https://read.nablaz.io/mcp" }.Both doors are rate-limited per client IP; a request over the limit gets 429 with a plain-text body. Beside them, GET /live (the process is up) answers with a status code and a short text, and GET /ready (the index has caught up) answers HTTP 200 with an empty body when ready, and 503 with {"ready":false} when not; nothing else is s
Only the beginning is shown; read the rest in the repo