Keeta Network MCP Server
Provides AI agents with native access to the Keeta Network Layer 1 blockchain for payments, asset transfers, and compliance-ready financial infrastructure. It features a dynamic, self-describing architecture that allows agents to automatically discover and execute SDK methods at runtime.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
schenkty
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
keeta_generate_seedGenerate a new random cryptographic seed for the Keeta Network. This is the starting point for all Keeta operations. A seed can derive unlimited accounts via keeta_derive_account. Store the seed securely — it controls all derived accounts and their funds. Returns: { seed: string }
keeta_derive_accountDerive a Keeta account (public/private keypair) from a seed and index. Each unique (seed, index, algorithm) combination produces a deterministic account. The returned address (keeta_...) is used in all other tools as account/token identifiers. Supported algorithms: - SECP256K1 (default) — most c…
keeta_request_test_tokensRequest free KTA tokens from the Keeta test network faucet. Only works on the test network. Sends 5 KTA to the given address for development/testing. KTA is needed for transaction fees on the network. Returns: { status, address, amountRequested, currentBalance }
keeta_get_network_configGet the configuration for a Keeta network, including the network ID, base token address, and network account address. This is useful for understanding the network you are operating on before making transactions. Returns: { networkAlias, networkId, baseToken, networkAddress }
keeta_list_sdk_methodsDiscover available methods and properties on Keeta SDK objects at runtime. Use this FIRST to understand what operations are available before calling execute tools. The "target" parameter accepts: Core SDK (fixed): "Client" → read-only network queries "UserClient" → authenticated op…
keeta_client_executeExecute any method on the Keeta Client (read-only network operations). Use keeta_list_sdk_methods with target "Client" to discover available methods. Common methods: getAccountInfo, getBalance, getAllBalances, getHeadBlock, getBlock, getHistory, getTokenSupply, getNetworkStatus, getPeers, getVersi…
keeta_user_client_executeExecute any method on the Keeta UserClient (authenticated operations requiring an account). Use keeta_list_sdk_methods with target "UserClient" to discover available methods. Common methods: allBalances, balance, head, chain, history, state, send, setInfo, generateIdentifier, updatePermissions, cr…
keeta_builder_executeExecute a sequence of operations using the UserClient Builder pattern, then optionally compute and publish. The builder batches multiple operations into blocks for efficient on-chain execution. Each operation in the "operations" array is an object with "method" and "args". Use keeta_list_sdk_metho…
keeta_anchor_executeExecute ANY anchor operation on the Keeta Network. Fully dynamic — auto-discovers services and lib modules from the SDK at runtime. subtarget types: - "service" → call a method on any anchor service client (FX, KYC, AssetMovement, Username, Notification, or ANY future service). Set serviceName to…
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
Tool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
9/9 tools missing one or more hints — keeta_generate_seed (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); keeta_derive_account (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); keeta_request_test_tokens (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +6 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool inputs are validated
7/9 tool handlers declare input schemas (78%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 1/9 tool handlers wrap calls in try/catch (11%)
Wrap each tool handler body in try/catch and return a structured error response.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tests exist
No test files found
Add tests that exercise each declared tool.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.1 (high), @modelcontextprotocol/sdk@1.12.1 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Domain consistency
npm scope @keetanetwork doesn't match GitHub owner schenkty
Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/schenkty/kta-mcp)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check