Skip to main content
Glama

Server Details

One MCP for your whole revenue stack plus contact enrichment at cost. Build your own back-office apps on the same data. Credentials stay in a vault.

Ownership verified

The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.

If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.

Status
Unhealthy
Uptime
0.0% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP
URL
ChatGPT
–
Claude
–

TDQS

C2.9/5.0

Scored across 369 tools

Disambiguation2/5

With 369 tools spanning ~40 connectors there are many near-neighbours: at least six overlapping people/email/phone lookups (apollo_match_person, linkedin_aiark_person, pipecorn, fullenrich_enrich_linkedin, lemlist_enrich, and the whole waterfall_* family), duplicate governance surfaces (oto_resource vs oto_resource_v2, oto_admin_doctrine vs oto_admin_guide), and read/act pairs that are easy to cross (gmail vs gmail_act, http_get/http_post vs http_act, github_files vs github_act). Individual descriptions are unusually careful, which keeps it above the floor, but at this scale an agent will routinely pick the wrong sibling.

Naming Consistency3/5

Most names are snake_case with a connector prefix, but the architecture is inconsistent: some connectors expose one verb-y tool per action (fr_get, fr_search, github_pulls) while others collapse everything into a single bare noun plus an `op` parameter (gmail, slack, mux, pipecorn, elevenlabs), and suffixes like _act, _app, _search, and the deprecated _v2 variant add noise. Readable, but no single predictable pattern holds across the catalogue.

Tool Count1/5

369 tools is an extreme mismatch for any single assistant surface; entire connectors (oto_admin_*, lemlist_*, apify_*, the French open-data stack, the foncier/urba GIS stack) would each justify a server of their own. A toolbox this size is only navigable through the meta-discovery tools (oto_list_my_tools, oto_call), which is itself an admission that the visible set is too large.

Completeness4/5

Coverage is genuinely broad: datastore CRUD plus schema/queue/history, docs, projects, procedures, runs, sharing, and dozens of external domains each with read/write/lifecycle verbs. Gaps exist at the edges (e.g. Slack only manages usergroups rather than full messaging, Resend segments cannot be deleted) but workarounds or alternate tools almost always exist, so agents rarely hit a dead end.

Publisher details

Operator
Tulina · Publisher source
Operator website
https://tulina.ai/
Vendor relationship
First-party
Privacy policy
Not provided
Restrictions
Paid plan of 299€/m per company · Publisher source

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Remote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.
      16
      11 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Browse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources