Addresses opus reviewer findings on the Task 5 commit (33c4b52). Important: - agent-network.ts (3 sites) and self-improvement.ts (2 sites): response copy no longer tells a caller to run vector_get_spend_limits (deleted in Task 5) after a safety-limit error. Replaced with "Server spend limits for this tool are set via VECTOR_SPEND_LIMIT_PER_TX / VECTOR_SPEND_LIMIT_DAILY" (matching each site's existing phrasing). Nothing else in either file touched - both stay custodial until PRs 7/8. Also reworded the two comments (of my own, from Task 5) that named the deleted tool - tool-inventory.test.ts's header docblock and rate-limit-gating.test.ts's probe-choice comment - so a final `grep -rn vector_get_spend_limits packages/` is clean except run.test.ts (Task 6's, left untouched as instructed). - boundary.test.ts: added a third test pinning CUSTODIAL_UNTIL_LATER_PR.size === 2, so PR 7/8 shrinking it is a visible, reviewable number change rather than a silent list edit. - boundary.test.ts: FORBIDDEN is no longer word-bounded (`/(mnemonic|seed|bip39|fromSeed|walletFromSeed|selectWallet\.fromSeed)/i`, \b dropped) so it catches `seedPhrase`, `WALLET_SEED`, `bip39x`-shaped vocabulary, not just whole-word matches. Verified empirically (not just by inspection) that this introduces zero new hits outside the two allowlisted files - grepped `seed`/`bip39`/`mnemonic` case-insensitively across all of packages/builder/src first, confirmed every hit was already confined to agent-network.ts/self-improvement.ts, then reran the full boundary suite to prove it: no benign collisions, nothing to report back before committing. Added a fourth test pinning every FORBIDDEN alternative against a fixture corpus (mnemonic/MNEMONIC/seedPhrase/WALLET_SEED/bip39/ fromSeed/walletFromSeed/selectWallet.fromSeed/seed all match; "address-only wallet"/"unsigned transaction"/"changeAddress" don't) so deleting an alternative from the regex fails a named test instead of silently narrowing the guard. Cheap folds: - vector.ts: the five build_* tool DESCRIPTIONS (not response copy - that already taught the confirm step as of Task 5) now end with "...then broadcast with vector_submit_transaction and confirm with vector_await_transaction." Regenerated the snapshot; verified structurally that the delta is description-field-only on exactly those five entries (inputSchema untouched, all 23 keys unchanged) - this is also what makes the Task 5 addition-A docblock's "descriptions teach the full flow" claim actually true end-to-end. - tool-inventory.test.ts: each per-tool test now also asserts 'description' in schemaSnapshot[toolName] before the deepStrictEqual, so a regen that silently drops a description (e.g. JSON.stringify eating an undefined value) fails by naming the tool, not as an opaque diff. - regen-tool-schemas.mjs: server entry point and snapshot output path are now resolved from import.meta.dirname instead of hardcoded repo-root-relative strings, so the script runs from any cwd. Verified by actually invoking it from packages/builder (not the repo root) and confirming it wrote to the one correct packages/builder/test/smoke/tool-schemas.snapshot.json. Full gate re-run after all of the above: typecheck 0 errors, test:unit 144/144 (140 baseline + 4 boundary tests, up from 2), test:smoke 26/26, test:integration:auth 12/12. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Vector MCP Server
MCP (Model Context Protocol) server for Vector - the Apex Fusion eUTXO L2. Enables AI agents (Claude, GPT, Gemini, or any MCP client) to interact with Vector natively: query balances, send transactions, deploy and interact with smart contracts, manage on-chain agent identities, and submit protocol improvement proposals.
Built on Ogmios + Koios - no Blockfrost dependency.
Vector mainnet is live. Full guides: Vector AI documentation.
Hosted servers - no install
Hosted instances run on both networks, exposing all 25 tools:
| Network | Endpoint |
|---|---|
| Mainnet | https://mcp.vector.mainnet.apexfusion.org/sse |
| Testnet | https://mcp.vector.testnet.apexfusion.org/sse |
Connect from Claude Code in one command:
claude mcp add --transport sse vector-mcp https://mcp.vector.mainnet.apexfusion.org/sse
Security notice — custody. Signing tools currently take your wallet mnemonic as a tool-call parameter. It therefore passes through your MCP client, your model provider, and the hosted server's memory — it is not written to disk, but it is exposed. Use only a hot wallet holding funds you can afford to lose, and prefer self-hosting until the non-custodial migration lands.
vector_submit_transactionandvector_await_transactionare the exception — they take no mnemonic and sign nothing; they only broadcast a transaction signed elsewhere (for example by a local signer) and poll for confirmation. See docs/architecture/non-custodial-split.md.
Self-hosting instructions are below.
Local signer (non-custodial path)
packages/signer is a local MCP server that holds your key and signs transactions locally
instead of handing your mnemonic to a shared host. It has no network access at all —
stdio transport, no Provider, no egress — so a key given to it never reaches a shared server
or your model provider.
See packages/signer/README.md for configuration, its tools, and
known limitations — including the gap that matters most right now: the hosted builder's tools
above still require your mnemonic as a call parameter, so pairing the signer with this
hosted builder does not yet remove the custody exposure described above. Closing that gap is
the next stage of the migration described in
docs/architecture/non-custodial-split.md; until
it ships, the security notice above still applies.
Features
- Wallet management - derive addresses from mnemonic, query balances and UTxOs
- Transactions - send AP3X and native tokens, build multi-output transactions, dry-run simulations
- Smart contracts - deploy Plutus/Aiken validators, lock and spend UTxOs at script addresses
- Agent registry - register, discover, update, transfer, and deregister on-chain AI agent identities via soulbound NFTs
- Agent messaging - send on-chain messages between agents via TX metadata
- Self-Improvement Module - browse, submit, critique, and endorse improvement proposals (live on Vector mainnet)
- Safety controls - per-transaction and daily spend limits, persistent audit log, rate limiting
- SSE transport - HTTP server with Server-Sent Events for MCP client connectivity
MCP Tools (25)
Wallet & Queries
| Tool | Description |
|---|---|
vector_get_balance |
Get AP3X and token balances for any address |
vector_get_address |
Get the wallet address, balance, and holdings from a mnemonic |
vector_get_utxos |
List UTxOs for an address or wallet |
vector_get_spend_limits |
Check spend limits, daily usage, and audit log |
vector_get_transaction_history |
Get transaction history for a wallet |
Transactions
| Tool | Description |
|---|---|
vector_send_apex |
Send AP3X (respects spend limits) |
vector_send_tokens |
Send native tokens with optional AP3X |
vector_build_transaction |
Build multi-output transactions (sign+submit or return unsigned CBOR) |
vector_dry_run |
Simulate a transaction without submitting - estimate fees and validate |
vector_submit_transaction |
Broadcast an already-signed transaction (for example one signed by the local signer) |
vector_await_transaction |
Wait for a submitted transaction to be confirmed on-chain |
Smart Contracts
| Tool | Description |
|---|---|
vector_deploy_contract |
Deploy a Plutus V1/V2/V3 or Aiken validator to the chain |
vector_interact_contract |
Lock AP3X at a script address or spend from it with a redeemer |
Agent Registry
| Tool | Description |
|---|---|
vector_register_agent |
Register an agent - mints a soulbound identity NFT and locks a 10 AP3X deposit |
vector_discover_agents |
Discover registered agents, filter by capability or framework (no wallet needed) |
vector_get_agent_profile |
Get an agent's full profile by DID (no wallet needed) |
vector_update_agent |
Update an agent's name, description, capabilities, framework, or endpoint |
vector_transfer_agent |
Transfer agent ownership to a new address |
vector_deregister_agent |
Deregister an agent - burns the identity NFT and returns the 10 AP3X deposit |
vector_message_agent |
Send an on-chain message to an agent via TX metadata (label 674) |
Self-Improvement Module
| Tool | Description |
|---|---|
vector_self_improvement_browse |
Browse improvement proposals, critiques, and endorsements |
vector_self_improvement_submit_proposal |
Submit an improvement proposal (stakes AP3X) |
vector_self_improvement_critique |
Critique a proposal - support, oppose, or propose amendments |
vector_self_improvement_endorse |
Endorse a proposal by staking AP3X |
vector_self_improvement_analyze_metrics |
Proposal metrics: activity, adoption rate, treasury health, engagement |
Agent DIDs follow the format: did:vector:agent:{policyId}:{nftAssetName}
Self-hosting
1. Install and build
npm install
npm run build
2. Configure environment (optional)
cp .env.example .env
# Edit .env with your endpoint URLs (defaults point to Vector testnet; mainnet URLs below)
The mnemonic is passed per-call by the MCP client rather than stored in the environment. This avoids environment dumps, but does not make it private — see the security notice above.
3. Run
npm start
# Server listens on port 3000 (configurable via PORT env var)
If this instance will be reachable by anyone but you, set MCP_AUTH_TOKENS first - see Configuration below.
4. Add to Claude Desktop
Add to your Claude Desktop MCP config (claude_desktop_config.json):
{
"mcpServers": {
"vector": {
"command": "node",
"args": ["/path/to/vector-mcp-server/packages/builder/build/index.js"],
"env": {
"VECTOR_OGMIOS_URL": "https://ogmios.vector.testnet.apexfusion.org",
"VECTOR_SUBMIT_URL": "https://submit.vector.testnet.apexfusion.org/api/submit/tx",
"VECTOR_KOIOS_URL": "https://koios.vector.testnet.apexfusion.org/",
"VECTOR_EXPLORER_URL": "https://vector.testnet.apexscan.org"
}
}
}
}
For mainnet, use the mainnet endpoint table below. (No local setup needed if you use the hosted servers above.)
Docker
npm run build
docker build -t vector-mcp .
docker run -p 3000:3000 vector-mcp
If this instance will be reachable by anyone but you, set MCP_AUTH_TOKENS first - see Configuration below (docker-compose.yml in this repo binds 127.0.0.1 by default; the command above does not).
Configuration
| Variable | Description | Default |
|---|---|---|
PORT |
HTTP server port | 3000 |
VECTOR_OGMIOS_URL |
Ogmios HTTP JSON-RPC endpoint | https://ogmios.vector.testnet.apexfusion.org |
VECTOR_KOIOS_URL |
Koios REST API endpoint | https://v2.koios.vector.testnet.apexfusion.org/ |
VECTOR_SUBMIT_URL |
Transaction submit API | https://submit.vector.testnet.apexfusion.org/api/submit/tx |
VECTOR_EXPLORER_URL |
Block explorer base URL | https://vector.testnet.apexscan.org |
VECTOR_SPEND_LIMIT_PER_TX |
Max lovelace per transaction | 100000000 (100 AP3X) |
VECTOR_SPEND_LIMIT_DAILY |
Max lovelace per day | 500000000 (500 AP3X) |
VECTOR_AUDIT_LOG_PATH |
Persistent audit log file path | ./vector-audit-log.json |
VECTOR_RATE_LIMIT_PER_MINUTE |
Max tool calls per minute | 60 |
MCP_AUTH_TOKENS |
Bearer tokens that may call this server. Comma-separated; each entry is label:token or a bare token. When unset, the server is open to anyone who can reach it. |
(unset — auth disabled) |
Running a public instance? Set
MCP_AUTH_TOKENS. Without it every caller is treated as one anonymous identity and shares a single rate-limit bucket, so one busy client throttles everyone. Rate limits are applied per identity, so give each client its own token.
Malformed values fail loudly, not silently. The server refuses to start if
MCP_AUTH_TOKENScontains an empty token, a token with embedded whitespace, a duplicate token, or a value where every comma-separated entry is blank (e.g. a stray,,,) — each raises a startup error that names the problem but never echoes a token value. Commas delimit entries and cannot be escaped, so generate tokens from a comma-free charset (hex / base64url / alphanumeric).
Mainnet endpoints
| Variable | Mainnet value |
|---|---|
VECTOR_OGMIOS_URL |
https://ogmios.vector.mainnet.apexfusion.org |
VECTOR_SUBMIT_URL |
https://submit.vector.mainnet.apexfusion.org/api/submit/tx |
VECTOR_KOIOS_URL |
https://v2.koios.vector.mainnet.apexfusion.org/ |
VECTOR_EXPLORER_URL |
https://vector.apexscan.org/en/ |
Testing
npm run test:unit
No wallet, no network — pure logic only (CBOR encode/decode assertions).
npm run test:smoke
Builds the server, boots it, and asserts the exposed tool inventory matches the checked-in snapshot. No wallet, no external network. CI runs this and test:unit on every PR.
echo "your mnemonic words here" > packages/builder/mnemonic.txt
npm run test:integration
Requires mnemonic.txt in packages/builder/ containing a funded Vector testnet mnemonic. Covers the core tools end-to-end against Vector testnet, including the full agent lifecycle: register, discover, profile, update, transfer, message, and deregister. Never runs in CI.
npm run test:smoke:signer
Builds the local signer (packages/signer), boots it over stdio, and exercises all four of
its tools, including the fail-closed audit-write-failure path. No wallet, no network. CI runs
this on every PR alongside the two smoke tests above.
export VECTOR_SIGNER_MNEMONIC_FILE=/absolute/path/to/testnet-mnemonic.txt
npm run test:integration:signer
Requires a funded Vector testnet wallet. Builds a real unsigned transaction the way the
hosted builder does (no key), then has the local signer decode, policy-check, and sign it
against live chain data. Never submits. Never runs in CI. See
packages/signer/README.md.
Architecture
┌──────────────────────┐ ┌──────────────────────────┐
│ Claude / GPT / etc. │◄────►│ vector-mcp-server │
│ (any MCP client) │ SSE │ │
└──────────────────────┘ │ ┌────────────────────┐ │
│ │ Rate Limiter │ │
│ │ (60 calls/min) │ │
│ └────────┬───────────┘ │
│ │ │
│ ┌────────▼───────────┐ │
│ │ Safety Layer │ │
│ │ - Per-tx limits │ │
│ │ - Daily limits │ │
│ │ - Audit log │ │
│ └────────┬───────────┘ │
│ │ │
│ ┌────────▼───────────┐ │
│ │ Lucid + Ogmios │ │
│ │ Provider │ │
│ └────────┬───────────┘ │
│ │ │
│ ┌────────▼───────────┐ │
│ │ Ogmios / Koios / │ │
│ │ Submit API │ │
│ └────────────────────┘ │
└──────────────────────────┘
About Vector
Vector is Apex Fusion's eUTXO L2, running Cardano mainnet parameters (Conway era, Plutus V3). Sub-1-second optimistic finality and deterministic fees make it a natural chain for AI agent workloads. Mainnet is live.
- Docs: https://apex-fusion.github.io/vector-ai-documentation/
- Explorer (mainnet): https://vector.apexscan.org/en/
- Explorer (testnet): https://vector.testnet.apexscan.org
- Apex Fusion: https://apexfusion.org