# io.github.Abstract36/stakechain (remote · stakechain-api.vercel.app)

Live Base staking/lending yields (APY, TVL, vaults) as MCP tools; x402 pay-per-request tier

- Trust score: 69/100 (medium)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `stakechain-api.vercel.app`: 69/100 (this document), [markdown](https://verifymcp.io/servers/abstract36-stakechain/stakechain-api.md), [page](https://verifymcp.io/servers/abstract36-stakechain/stakechain-api)
- npm · `stakechain-mcp`: 69/100, [markdown](https://verifymcp.io/servers/abstract36-stakechain/stakechain-mcp.md), [page](https://verifymcp.io/servers/abstract36-stakechain/stakechain-mcp)

## Channel facts

- Endpoint: `https://stakechain-api.vercel.app/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.3.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 6 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1476 tokens (~246/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the io.github.Abstract36/stakechain MCP server?

io.github.Abstract36/stakechain is a hosted endpoint at https://stakechain-api.vercel.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http abstract36-stakechain 'https://stakechain-api.vercel.app/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "abstract36-stakechain": {
      "url": "https://stakechain-api.vercel.app/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "abstract36-stakechain": {
      "type": "http",
      "url": "https://stakechain-api.vercel.app/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.abstract36-stakechain]
url = "https://stakechain-api.vercel.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "abstract36-stakechain": {
      "type": "remote",
      "url": "https://stakechain-api.vercel.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add abstract36-stakechain --url 'https://stakechain-api.vercel.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  abstract36-stakechain:
    url: "https://stakechain-api.vercel.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "abstract36-stakechain": {
      "Transport": "http",
      "Url": "https://stakechain-api.vercel.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add abstract36-stakechain -t streamable-http -u 'https://stakechain-api.vercel.app/mcp'
```

### Other

```json
{
  "mcpServers": {
    "abstract36-stakechain": {
      "type": "http",
      "url": "https://stakechain-api.vercel.app/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 68, 0)

- [security] Tool “list_base_yields” rewrote its description, which is the text the model reads
- [security] Tool “list_lending_vaults” rewrote its description, which is the text the model reads

### 2026-11-01 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 67, −1)

- [security] Tool “yield_history” rewrote its description, which is the text the model reads
- [security] Tool “list_lending_vaults” rewrote its description, which is the text the model reads
- [security] Tool “best_yield” rewrote its description, which is the text the model reads
- [security] Tool “list_base_yields” rewrote its description, which is the text the model reads
- [security] Tool “market_profile” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional] Schema quality: good → excellent
- [functional] New tool “build_deposit”

### 2026-10-30 (score 68, +1)

- [security] Tool “list_lending_vaults” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 59 → 78
- [functional] New tool “market_profile”
- [functional] New tool “yield_history”

### 2026-10-29 (score 67, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-28 (score 67)

First indexed and scored.

## MCP tools (6)

### `list_base_yields` (~294 tokens)

Survey staking and lending opportunities on Base: APY, TVL, project and asset for each. 

Use this for breadth — browsing the market, answering 'what is available', or filtering a wide set. It covers pools this server cannot deposit into as well as ones it can.

Use something else when: you want one asset's single best option (`best_yield`); you intend to deposit and need a contract address (`list_lending_vaults`); you are judging one market rather than comparing many (`market_profile`).

Every row says where its number came from: `source` is `onchain` (read from the protocol's contracts at `block`, so the figure can be re-derived), `morpho-api`, or `defillama` — a third-party snapshot that carries no Moonwell USDC market at all and understates Aave's Base reserve.

Ranks by TVL unless sortByApy is set. Four-digit emission farms are filtered out by default. Returns market data, not a recommendation; any row's `pool` id can be passed to `yield_history`.

Input parameters:

- `asset` (string): Filter by asset symbol, e.g. ETH, USDC
- `minTvl` (number): Minimum TVL in USD
- `sortByApy` (boolean): Sort by APY descending
- `stable` (boolean): Only stablecoin pools

### `best_yield` (~175 tokens)

The single highest-APY pool on Base for one asset, with junk-farm filters applied (minimum TVL, APY ceiling, no impermanent-loss exposure).

Use this for a direct 'where is the best rate for X' question when one answer is wanted rather than a list.

Use something else when: you want to compare several options (`list_base_yields`); you intend to deposit (`list_lending_vaults` returns the address).

Important: it ranks by rate alone. A high answer here is a starting point, not a verdict — follow it with `market_profile` for the curator's cut and whether the money can be withdrawn, and `yield_history` for whether the rate has held.

Input parameters:

- `asset` (string, required): Asset symbol, e.g. ETH, USDC, cbBTC

### `list_lending_vaults` (~201 tokens)

The Base lending shelf an agent can act on: Morpho ERC-4626 vaults, Aave V3 reserves, Moonwell markets and this project's own staking pools, each with the contract address to deposit into (`depositTo`), the asset's address and decimals, and a `risk` block (fee, age, concentration, utilisation, incentive share).

Use this whenever a deposit might follow, or when you need a market id to pass to `market_profile` or `yield_history`.

Use `list_base_yields` instead when surveying the wider market, including pools that cannot be deposited into here.

Rates for Aave and Moonwell are read from their own contracts, so markets missing from aggregator snapshots appear here. Each row carries `source` and `block`: an `onchain` row can be re-read at that block and checked, a `morpho-api` row comes from Morpho's own GraphQL.

### `market_profile` (~344 tokens)

Risk profile for one market, for the moment before capital is committed.

Use this when a specific market has been chosen and the question is whether to go ahead. It is the one tool that answers 'what else should I know besides the rate'.

Use something else when: you are still choosing between markets (`list_base_yields`, `best_yield`); you only want to know whether the rate moved (`yield_history`); you need the deposit address (`list_lending_vaults`).

Prerequisite: the market must be on this server's shelf — a vault, reserve or pool from `list_lending_vaults`. Arbitrary pool ids from `list_base_yields` will not resolve.

Returns `score` (0-100) and `band` ('solid', 'fair', 'thin' or 'fragile'), plus a `signals` object holding the six inputs behind it: size (TVL), track_record (days running), stability (APY volatility from daily snapshots), yield_quality (share of the APY that is borrower interest rather than incentives that can stop), cost (the curator's percentage cut) and diversification (share sitting in the largest position). Each signal carries its raw value and its sub-score, and `method.weights` gives the weighting, so the score can be recomputed. A signal lacking data reports score null and is excluded from the weighting rather than guessed at. Pair with `yield_history` for an unusually high rate. Describes what has happened, not what will.

Input parameters:

- `pool` (string, required): Vault symbol, address, or protocol-asset (e.g. sparkusdc, aave-usdc)

### `yield_history` (~192 tokens)

Daily APY and TVL history for one market, with min, median, max and volatility over the window.

Use this for one question only: has this rate held, or did it appear yesterday? Call it before acting on any unusually high rate.

Use something else when: you want the other risk factors — fee, size, utilisation, concentration — which are in `market_profile`; you are still choosing a market (`list_base_yields` or `best_yield`).

Prerequisite: a market id from one of the list tools. Check `observations` before concluding anything — a market added recently has few snapshots, and a short series is not evidence of stability.

Input parameters:

- `days` (number): Look-back window in days, default 30
- `pool` (string, required): Market id: a pool id from list_base_yields, or vault:<address> from list_lending_vaults

### `build_deposit` (~270 tokens)

Turns a chosen market into signed-ready calldata: an ordered list of transactions to deposit into it or leave it, across Morpho vaults, Aave reserves, Moonwell markets and this project's staking pools — three different protocol interfaces behind one call. The approve step is included only when the current allowance does not already cover the amount, read on-chain at request time.

Use this once a market has been chosen and the decision is made.

Use something else when: still choosing (`list_lending_vaults`, `best_yield`); weighing whether to go ahead (`market_profile`, `yield_history`).

Nothing is signed or sent — the caller holds the keys. Simulate before sending. `amount: "all"` on a withdrawal exits by share rather than by figure, so interest accruing between the call and the block is not left behind.

Input parameters:

- `action` (string): Defaults to deposit
- `amount` (string, required): Whole asset units, e.g. '25.5' — or 'all' to exit a position completely
- `from` (string, required): The address that will sign and hold the position
- `pool` (string, required): Market id from list_lending_vaults, e.g. 'sparkusdc', 'aave-usdc', 'mUSDC'

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/abstract36-stakechain/stakechain-api#diagnostics

## Score history

- 2026-11-05: 69
- 2026-11-04: 69
- 2026-11-03: 68
- 2026-11-02: 68
- 2026-11-01: 68
- 2026-10-31: 67
- 2026-10-30: 68
- 2026-10-29: 67
- 2026-10-28: 67

## Common questions

### What is the io.github.Abstract36/stakechain MCP server?

io.github.Abstract36/stakechain is an MCP server listed in the public MCP registry as io.github.Abstract36/stakechain. Live Base staking/lending yields (APY, TVL, vaults) as MCP tools; x402 pay-per-request tier. This page covers its hosted endpoint (https://stakechain-api.vercel.app/mcp).

### Is the io.github.Abstract36/stakechain MCP server safe to use?

io.github.Abstract36/stakechain scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.Abstract36/stakechain MCP server expose?

io.github.Abstract36/stakechain exposes 6 tools: list_base_yields, best_yield, list_lending_vaults, market_profile, yield_history, build_deposit. Their descriptions and schemas cost roughly 1,476 tokens of context every time the server is loaded.

### Does the io.github.Abstract36/stakechain MCP server require authentication?

No. We connected to io.github.Abstract36/stakechain without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the io.github.Abstract36/stakechain MCP server still maintained?

io.github.Abstract36/stakechain is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://stakechain-api.vercel.app/mcp
- Repository: https://github.com/Abstract36/StakeChain
- Changelog RSS feed: https://verifymcp.io/servers/abstract36-stakechain/stakechain-api.xml
- Changelog JSON feed: https://verifymcp.io/servers/abstract36-stakechain/stakechain-api.json
- HTML version of this page: https://verifymcp.io/servers/abstract36-stakechain/stakechain-api