CtrlK
BlogDocsLog inGet started
Tessl Logo

add-agents-mcp-server

Add an MCP (Model Context Protocol) server to a Mattermost plugin so the Agents plugin can call its tools. Use when implementing cross-plugin MCP, exposing AI tools from a Mattermost plugin to the Agents plugin, or wiring up the `pluginmcp` helper from mattermost-plugin-agents.

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced skill body with executable Go code, explicit validation, and useful gotchas. It is concise enough and well-structured, with the only real weakness being a monolithic single-file layout that could split some reference material out.

Suggestions

Move the full Configuration reference and API reference blocks into a separate references file (e.g. references/api.md) and link to it from the body, leaving only the essential snippets inline to reduce SKILL.md length.

Trim a few explanatory sentences that restate what the code already shows (e.g., the sync.RWMutex justification, Register retry cadence) to tighten conciseness further.

Consider extracting the full mcp.go and mcp_tools.go listings into a references/ template file, keeping only the key structural excerpts inline.

DimensionReasoningScore

Conciseness

Largely efficient with executable code and targeted operational prose; a few explanatory sentences (e.g., the lock's purpose, Register retry behavior) could be trimmed but mostly earn their place, fitting 'efficient; minor instances of over-explanation'.

4 / 5

Actionability

Copy-paste-ready Go code, concrete shell commands (git switch -c, go mod tidy, make test), and specific examples covering the common cases — fully executable guidance.

5 / 5

Workflow Clarity

A clear eight-phase sequence (Phase 0–8) with explicit validation checkpoints in Phase 8 (build, test, check-style, manual e2e) and error-feedback loops for registration retries.

5 / 5

Progressive Disclosure

No bundle files exist, so all content is inline in one ~370-line SKILL.md; it is well-organized into clear sections (Phases, Configuration/API reference, Constraints, Troubleshooting, References), but a long single file with API reference and full code inline leaves minor organization gaps versus ideal splitting.

4 / 5

Total

18

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A tight, third-person description that cleanly states both capability and trigger conditions for a well-scoped niche. It is specific, distinct, and actionable with only minor keyword-coverage gaps.

DimensionReasoningScore

Specificity

Names the domain (Mattermost plugin MCP) and several concrete actions — 'Add an MCP server', 'exposing AI tools', 'wiring up the pluginmcp helper' — with only minor coverage gaps, fitting the 'lists several specific actions' anchor.

4 / 5

Completeness

Explicitly answers both what ('Add an MCP server to a Mattermost plugin so the Agents plugin can call its tools') and when ('Use when implementing cross-plugin MCP, exposing AI tools..., or wiring up the pluginmcp helper') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural-keyword coverage ('MCP', 'Model Context Protocol', 'cross-plugin MCP', 'Mattermost plugin', 'Agents plugin', 'pluginmcp helper') with synonyms, though a few natural variations are absent — good but not fully comprehensive.

4 / 5

Distinctiveness Conflict Risk

A clear narrow niche (cross-plugin MCP for the Mattermost Agents plugin) with distinct triggers and minimal realistic overlap with other skills.

5 / 5

Total

18

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

relative_links

Relative link issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
mattermost/mattermost-ai-marketplace
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.