Loading ToolBench

Reading the current corpus…

sociona-mcp-server MCP server · C · ToolBench

sociona-mcp-server

MCP server for Sociona social media API - interact with social media platforms through AI assistants and MCP-compatible tools

2026-07-28+STDIO7 tools

60/100

Definition Quality76

Protocol Readiness50

Supportability40

Spec posture

Inferred effective spec 2026-07-28+·current baseline 2026-07-28

Static source inference · medium confidence · evidence: stateless requests

Current-spec patterns detected

Summary

Server has 7 well-structured tools with complete input schemas using Zod validation and clear enum constraints. All tools have descriptions and parameters are typed. However, output schemas are not documented, responses are text-only without structured field definitions. Error handling exists but lacks recovery guidance. Tool names follow verb_noun convention well. Parameter descriptions are adequate but could be more prescriptive about constraints and formats. No tool annotations (readOnlyHint/destructiveHint) despite clear risk levels. Missing pagination for list tools and no documented output structure for agents to parse.

Tools (7)

cancel_scheduled_postdestructiveauthsource verified77/100

Cancel a scheduled post before it publishes

get_accountsread onlyauthsource verified75/100

Get list of connected social media accounts

get_post_statsread onlyauthsource verified72/100

Get statistics about your posts

get_postsread onlyauthsource verified75/100

Get recent posts published via the API

get_scheduled_postsread onlyauthsource verified75/100

Get scheduled posts, optionally filtered by status

publish_postwriteauthsource verified80/100

Publish a social media post immediately

schedule_postwriteauthsource verified80/100

Schedule a post for future publication

Issues (5)

HIGHresponse-shaper ↗

No output schemas documented. Tools return text-only responses without structured field definitions. LLMs cannot parse results to extract IDs, timestamps, or metadata for downstream tool chaining.

publish_postschedule_postget_accountsget_postsget_scheduled_postscancel_scheduled_postget_post_stats

HIGHtool-annotations ↗

No tool annotations (readOnlyHint, destructiveHint, idempotentHint) despite clear risk levels (WRITE, DESTRUCTIVE, READ_ONLY). Agents cannot determine which tools are safe to retry or have side effects.

publish_postschedule_postcancel_scheduled_post

HIGHpaginated-result ↗

List tools (get_posts, get_scheduled_posts, get_accounts) lack pagination parameters (offset/limit/cursor) and do not document result limits. Large result sets will blow context windows.

get_postsget_scheduled_postsget_accounts

Recommendations

Add structured output schemas to all tools. Document return fields (post_id, status, published_at, etc.) so agents can extract and chain results. Use JSON Schema to define response structure.
Implement tool annotations: mark publish_post and schedule_post with destructiveHint=true; mark get_* tools with readOnlyHint=true; mark schedule_post with idempotentHint=true if scheduling the same post twice is safe.
Add pagination to get_posts, get_scheduled_posts, and get_accounts. Include offset/limit parameters (default limit=50, max=100) and return total_count and next_cursor in responses.
Enhance error messages with recovery guidance. E.g., 'No X account connected. Call get_accounts() to see available platforms, or connect a new account at https://sociana.app/settings.'
Document parameter format constraints in descriptions. E.g., 'scheduledFor: ISO 8601 datetime string (YYYY-MM-DDTHH:mm:ssZ), must be in the future, minimum 5 minutes from now.'

Score history

Overall score trend

First recorded score · v2 rubric

60/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	C	60	2026-07-28+	v2