# SigRank — AI Operator Benchmarking (remote · signalaf.com)

SigRank benchmark MCP: cascade metrics, leaderboard, operator profiles, simulation, diagnostics.

- Trust score: 78/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `signalaf.com`: 78/100 (this document), [markdown](https://verifymcp.io/servers/com-signalaf-sigrank/api-mcp.md), [page](https://verifymcp.io/servers/com-signalaf-sigrank/api-mcp)

## Channel facts

- Endpoint: `https://signalaf.com/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-09-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - 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**: 76/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 4383 tokens (~182/item across 24 items; 16 tools + 8 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability check failed: schema churn in the 25 days we've observed: 0 tool removals, 15 breaking changes, 0 auth/transport breaks, 1 additions.
- **Tool Coverage**: 93/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 74% of tool parameters carry a description.
  - Structured output schemas are declared (25% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the SigRank — AI Operator Benchmarking MCP server?

SigRank — AI Operator Benchmarking is a hosted endpoint at https://signalaf.com/api/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 com-signalaf-sigrank 'https://signalaf.com/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-signalaf-sigrank": {
      "url": "https://signalaf.com/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-signalaf-sigrank": {
      "type": "http",
      "url": "https://signalaf.com/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-signalaf-sigrank]
url = "https://signalaf.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-signalaf-sigrank": {
      "type": "remote",
      "url": "https://signalaf.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-signalaf-sigrank --url 'https://signalaf.com/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-signalaf-sigrank:
    url: "https://signalaf.com/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-signalaf-sigrank": {
      "Transport": "http",
      "Url": "https://signalaf.com/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-signalaf-sigrank -t streamable-http -u 'https://signalaf.com/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-signalaf-sigrank": {
      "type": "http",
      "url": "https://signalaf.com/api/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.

### 2026-09-21 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 29 to 33.

### 2026-09-19 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 22 to 26.

### 2026-09-17 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 16 to 19.

### 2026-09-15 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 9 to 13.

### 2026-09-12 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 0 to 3.

### 2026-09-08 (score 73, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-09-04 (score 73, −5)

- [security regression] Stability: 0.23 → fail
- [security regression] A breaking change shipped without a version bump: still 1.0.0
- [functional regression] Schema quality: 111 → 182
- [functional regression] “benchmark_me” added a required parameter “context”, so existing callers break
- [functional regression] “compare_to_field” added a required parameter “context”, so existing callers break
- [functional regression] “diagnose_cascade” added a required parameter “context”, so existing callers break
- [functional regression] “field_anomaly” added a required parameter “context”, so existing callers break
- [functional regression] “get_leaderboard” added a required parameter “context”, so existing callers break
- [functional regression] “get_operator” added a required parameter “context”, so existing callers break
- [functional regression] “get_sigrank_standard_record” added a required parameter “context”, so existing callers break
- [functional regression] “operator_gap” added a required parameter “context”, so existing callers break
- [functional regression] “operator_signature” added a required parameter “context”, so existing callers break
- [functional regression] “rank_if” added a required parameter “context”, so existing callers break
- [functional regression] “rank_paste” added a required parameter “context”, so existing callers break
- [functional regression] “rank_windows” added a required parameter “context”, so existing callers break
- [functional regression] “self_improve” added a required parameter “context”, so existing callers break
- [functional regression] “simulate_change” added a required parameter “context”, so existing callers break
- [functional regression] “suggest_improvements” added a required parameter “context”, so existing callers break
- [functional regression] “who_operates_like_me” added a required parameter “context”, so existing callers break
- [functional improvement] Tool coverage: 69% → 74%
- [functional] Schema quality: excellent → good

### 2026-09-03 (score 78, +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.

## MCP tools (16)

### `rank_paste` (~214 tokens)

Rank Paste — Local Token Cascade Calculator

Calculate SigRank cascade metrics from four non-negative token counts without submitting data. Returns Yield, Leverage, Velocity, SNR, and 10xDEV. No data is persisted.

Input parameters:

- `cache_read` (number, required): Tokens read from prompt cache (reused context).
- `cache_write` (number, required): Tokens written to prompt cache (new context stored for reuse).
- `context` (string, required): Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVE…
- `input` (number, required): Total input tokens consumed in the session.
- `output` (number, required): Total output tokens generated.

Output parameters:

- `cache_read` (number): Echoed cache-read token count.
- `cache_write` (number): Echoed cache-write token count.
- `dev10x` (number|null): log₁₀(Leverage). Logarithmic context amplification.
- `input` (number): Echoed input token count.
- `leverage` (number|null): Leverage = cache_read / input. Reusable context amplification. Null when input is zero.
- `non_compounding` (boolean): True if cache_write is zero (no compounding context).
- `output` (number): Echoed output token count.
- `snr` (number|null): Signal-to-noise ratio = output / (input + output). Null when input is zero.
- `velocity` (number|null): Velocity = output / input. Output per unit of input. Null when input is zero.
- `yield_` (number|null): Yield (Υ) = (cache_read × output) / input². Headline cascade efficiency. Null when input is zero.

### `get_sigrank_standard_record` (~280 tokens)

Export SigRank Standard Record

Build a SigRank Standard v0.1-draft portable operator record from available token telemetry. Input and output are required; unavailable cache telemetry remains null. Computes only the five-metric portable core through @sigrank/cascade and does not submit or persist data.

Input parameters:

- `cache_read` (integer|null): Cache-read tokens, or null when unavailable.
- `cache_write` (integer|null): Cache-write / cache-creation tokens, or null when unavailable.
- `context` (string, required): Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVE…
- `input` (integer, required): Fresh input tokens.
- `model` (string): Optional model identifier.
- `output` (integer, required): Output tokens.
- `provider` (string): Optional provider identifier.
- `timestamp` (string): Optional ISO-8601 timestamp. Defaults to the current time.
- `tool` (string): Optional tool/client identifier.

Output parameters:

- `metrics` (object)
- `source` (object)
- `spec`
- `telemetry` (object)
- `timestamp` (string)
- `warnings` (array)

### `get_leaderboard` (~191 tokens)

Get Leaderboard — Public Operator Rankings

Read the current public SigRank operator leaderboard. Returns ranked operators with Yield, Leverage, class tier, and display name.

Input parameters:

- `context` (string, required): Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVE…
- `limit` (integer): Maximum number of operators to return (1–100, default 25).
- `window` (string): Time window for the leaderboard: 7d, 30d, 90d, or all_time.

Output parameters:

- `entries` (array)
- `total_operators` (integer): Number of operators returned.
- `window` (string): The time window used for the query.

### `get_operator` (~176 tokens)

Get Operator — Public Profile by Codename

Read one public operator profile by codename. Returns class tier, rank, percentile, Yield, Leverage, Velocity, and SNR.

Input parameters:

- `codename` (string, required): The operator's unique codename (e.g. signal-ae3b5c3c55). Not the display name.
- `context` (string, required): Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVE…

Output parameters:

- `class_tier` (string): Operator class tier.
- `codename` (string): Operator's unique codename.
- `display_name` (string): Human-readable display name.
- `leverage` (number|null): Leverage if compounding, else null.
- `percentile` (number): Percentile in the public field.
- `rank` (integer): Global rank position.
- `snr` (number|null): Signal-to-noise ratio.
- `velocity` (number|null): Velocity = output / input.
- `yield_` (number|null): Yield (Υ) if compounding, else null.

### `simulate_change` (~276 tokens)

Simulate Change — What-If Cascade Predictor

Prescriptive 'what if' tool — takes your current 4 token pillars and proposed changes, runs the cascade on both, returns the exact Υ Yield delta, class change, and per-metric diffs. Test proposed pillar changes and see the payoff before changing your workflow. Changes can be absolute numbers (replace) or strings starting with +/- for relative deltas.

Input parameters:

- `cache_read` (number, required): Current cache-read tokens.
- `cache_write` (number, required): Current cache-write tokens.
- `changes` (object, required): Proposed changes. Keys: input, output, cache_read, cache_write. Values are absolute numbers (replace) or strings starting with +/- for relative deltas. Omitted pillars are unchanged.
- `context` (string, required): Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVE…
- `input` (number, required): Current input tokens.
- `output` (number, required): Current output tokens.

### `diagnose_cascade` (~237 tokens)

Diagnose Cascade — Efficiency Leak Finder

Analyzes your token cascade and diagnoses where you're leaking efficiency. Takes 4 token pillars and produces a ranked list of efficiency leaks with severity (critical/warning/info), findings, recommendations, and estimated Υ impact. Checks: cache leverage, velocity, SNR, cache creation ratio, input bloat, and 10xDEV compounding. Use this before simulate_change to understand what's wrong.

Input parameters:

- `cache_read` (number, required): Cache-read tokens.
- `cache_write` (number, required): Cache-write tokens.
- `context` (string, required): Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVE…
- `input` (number, required): Total input tokens.
- `output` (number, required): Total output tokens.

### `suggest_improvements` (~239 tokens)

Suggest Improvements — Ranked Yield Optimizer

Generates ranked, simulated improvement suggestions for your token cascade. Takes 4 token pillars, tests multiple strategies (increase cache reads, reduce input, increase output, optimize cache creation), simulates each, and returns them ranked by Υ yield impact. Each suggestion includes the action, pillar to change, projected Υ, yield delta, projected class, and rationale. Returns the single highest-impact change as best_single_change.

Input parameters:

- `cache_read` (number, required): Cache-read tokens.
- `cache_write` (number, required): Cache-write tokens.
- `context` (string, required): Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVE…
- `input` (number, required): Total input tokens.
- `output` (number, required): Total output tokens.

### `self_improve` (~250 tokens)

Self-Improve — One-Click Cascade Optimizer

Runs the full self-improvement cycle in one call: (1) computes your current cascade from 4 token pillars, (2) diagnoses efficiency leaks, (3) generates ranked improvement suggestions, (4) simulates the top suggestion, and (5) returns the complete cycle: diagnosis + suggestions + simulated impact of the best change. The 'one-click optimize' tool — call it at the end of a session to see what to improve next time.

Input parameters:

- `cache_read` (number, required): Cache-read tokens.
- `cache_write` (number, required): Cache-write tokens.
- `context` (string, required): Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVE…
- `input` (number, required): Total input tokens.
- `output` (number, required): Total output tokens.

### `rank_windows` (~257 tokens)

Rank Windows — Multi-Window Cascade

Score up to 4 time windows (7d, 30d, 90d, all-time) in one call. Each window is scored independently with the full cascade (Υ, SNR, Leverage, Velocity, 10xDEV, class). Omit windows you don't have — partial input is allowed (1-4 windows). Does NOT submit to the board.

Input parameters:

- `30d` (object): 30-day window token pillars (optional)
- `7d` (object): 7-day window token pillars (optional)
- `90d` (object): 90-day window token pillars (optional)
- `all` (object): All-time window token pillars (optional)
- `context` (string, required): Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVE…

### `benchmark_me` (~325 tokens)

Benchmark Me — Field Position Analyzer

Answers 'How good am I?' — benchmarks your token cascade against the live field. Takes 4 token pillars (or a codename), computes your cascade, then compares against the live leaderboard: percentile, rank, distance from median, distance from top 10%, strongest metric, weakest metric, and a one-line interpretation. This is the human-question tool — use it when someone asks 'am I a power user?' or 'how do I compare?'.

Input parameters:

- `cache_read` (number): Cache-read tokens. Required if codename is not provided.
- `cache_write` (number): Cache-write tokens. Required if codename is not provided.
- `codename` (string): Operator codename (alternative to providing pillars). If provided, fetches live profile from the board.
- `context` (string, required): Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVE…
- `input` (number): Total input tokens. Required if codename is not provided.
- `output` (number): Total output tokens. Required if codename is not provided.
- `window` (string): Time window for field comparison (default 30d).

### `rank_if` (~317 tokens)

Rank If — Counterfactual Rank Simulator

Answers 'What would it take to reach a target rank?' — takes your current 4 token pillars and a target percentile (e.g. 90 for top 10%), then simulates the smallest metric changes needed to reach that position. Returns: current rank/percentile, simulated rank/percentile, the specific pillar changes required, and the yield delta. This turns SigRank from a scoreboard into a simulator. Use it when someone asks 'what would move my rank?' or 'how do I get to top 10%?'.

Input parameters:

- `cache_read` (number, required): Current cache-read tokens.
- `cache_write` (number, required): Current cache-write tokens.
- `context` (string, required): Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVE…
- `input` (number, required): Current input tokens.
- `output` (number, required): Current output tokens.
- `target_percentile` (number, required): Target percentile (0-100). E.g. 90 for top 10%, 99 for top 1%.
- `window` (string): Time window for field comparison (default 30d).

### `operator_gap` (~296 tokens)

Operator Gap — What Separates Two Operators

Answers 'What specifically separates operator A from operator B?' — not just 'A has more Yield', but the primary cause, secondary cause, and offsetting weakness. Takes two codenames or two sets of pillars, computes both cascades, and decomposes the yield gap into leverage, velocity, SNR, and scale contributions. Returns the most explanatory factor.

Input parameters:

- `a_cache_read` (number)
- `a_cache_write` (number)
- `a_codename` (string): Codename for operator A (alternative to a_* pillars)
- `a_input` (number)
- `a_output` (number)
- `b_cache_read` (number)
- `b_cache_write` (number)
- `b_codename` (string): Codename for operator B (alternative to b_* pillars)
- `b_input` (number)
- `b_output` (number)
- `context` (string, required): Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVE…

### `field_anomaly` (~188 tokens)

Field Anomaly — Unusual Patterns in the Leaderboard

Finds unusual operators, metric relationships, and outliers in the live leaderboard — without user prompting. Returns: highest velocity among below-median leverage operators, only top-50 operator with near-zero cache write, largest 30-day yield improvement, rarest signature, and extreme divergence. Powers automated micro-marketing and field insights.

Input parameters:

- `context` (string, required): Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVE…
- `window` (string)

### `who_operates_like_me` (~260 tokens)

Who Operates Like Me — Nearest Neighbor Finder

Finds operators whose operating signature most resembles yours. Takes 4 pillars or a codename, computes your signature, then searches the live leaderboard for the nearest neighbors by signature distance. Returns: nearest operators, similarity %, where they outperform you, where you outperform them, and what separates you from the better operator. Makes the leaderboard feel like a network, not a list.

Input parameters:

- `cache_read` (number)
- `cache_write` (number)
- `codename` (string): Operator codename (alternative to pillars)
- `context` (string, required): Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVE…
- `input` (number)
- `limit` (number): Number of nearest neighbors to return (default 5)
- `output` (number)
- `window` (string)

### `compare_to_field` (~244 tokens)

Compare to Field — You vs Field vs Top 10% vs Top 1%

Creates a 'YOU vs FIELD vs TOP 10% vs TOP 1%' comparison table for your cascade metrics. Takes 4 pillars or a codename, fetches the live leaderboard, and returns your metrics alongside field median, top quartile, top decile, and top percentile for yield, leverage, velocity, and SNR. Simple, useful, and immediately understandable.

Input parameters:

- `cache_read` (number)
- `cache_write` (number)
- `codename` (string): Operator codename (alternative to pillars)
- `context` (string, required): Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVE…
- `input` (number)
- `output` (number)
- `window` (string)

### `operator_signature` (~232 tokens)

Operator Signature — Portable Identity Object

Computes a normalized operating signature from 4 token pillars or a codename. Returns a signature code, a legacy six-label signature_label, dominant trait, and closest comparable operators from the live board. The deprecated archetype field is retained as a compatibility alias; these labels are not the 10-type Build Archetypes reference extension.

Input parameters:

- `cache_read` (number)
- `cache_write` (number)
- `codename` (string): Operator codename (alternative to pillars)
- `context` (string, required): Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVE…
- `input` (number)
- `output` (number)
- `window` (string)

## Diagnostics

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

## Score history

- 2026-09-21: 78
- 2026-09-20: 77
- 2026-09-19: 77
- 2026-09-18: 76
- 2026-09-17: 76
- 2026-09-16: 75
- 2026-09-15: 75
- 2026-09-14: 74
- 2026-09-13: 74
- 2026-09-12: 74
- 2026-09-11: 73
- 2026-09-10: 73
- 2026-09-09: 73
- 2026-09-08: 73
- 2026-09-07: 73
- 2026-09-06: 73
- 2026-09-05: 73
- 2026-09-04: 73
- 2026-09-03: 78
- 2026-09-02: 77
- 2026-09-01: 77
- 2026-08-31: 76
- 2026-08-30: 76
- 2026-08-29: 75
- 2026-08-28: 75
- 2026-08-27: 73

## Common questions

### What is the SigRank — AI Operator Benchmarking MCP server?

SigRank — AI Operator Benchmarking is an MCP server listed in the public MCP registry as com.signalaf/sigrank. SigRank benchmark MCP: cascade metrics, leaderboard, operator profiles, simulation, diagnostics. This page covers its hosted endpoint (https://signalaf.com/api/mcp).

### Is the SigRank — AI Operator Benchmarking MCP server safe to use?

SigRank — AI Operator Benchmarking scores 78 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 SigRank — AI Operator Benchmarking MCP server expose?

SigRank — AI Operator Benchmarking exposes 16 tools: rank_paste, get_sigrank_standard_record, get_leaderboard, get_operator, simulate_change, and 11 more. Their descriptions and schemas cost roughly 3,982 tokens of context every time the server is loaded.

### Does the SigRank — AI Operator Benchmarking MCP server require authentication?

No. We connected to SigRank — AI Operator Benchmarking without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the SigRank — AI Operator Benchmarking MCP server still maintained?

SigRank — AI Operator Benchmarking is still listed as active in the MCP registry. We last reached this channel on 21 September 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://signalaf.com/api/mcp
- Repository: https://github.com/SunrisesIllNeverSee/sigrank-app
- Website: https://signalaf.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-signalaf-sigrank/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-signalaf-sigrank/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-signalaf-sigrank/api-mcp