Film MCP server
Which servers in the official MCP registry are Film's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-19
- Registry namefun.film.splice/splice-docsverified in the MCP registry
The registry name sits under film.fun. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-19
- Tools6
- Server calls itselfsplice-docs
- Server version1.3.0
- Protocol version2025-06-18
On 2026-10-19 the server answered initialize and tools/list without a sign-in. First answer in 139 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 3 of the 7 days it takes to judge reliability.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
- Answeredmeasuring3 of the 7 daily checks it takes to print a share
- Median first answer230 ms
- Space in an agent's context≈ 813 tokensthe definitions of all its tools (6), which an agent carries on every turn
- Tool definitionsA · 97 of 100
- Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 1 of 6
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
search_docsKeyword search over the Splice agent docs (getting started, authentication, MCP servers, pricing). Returns the best-matching sections with their text. Use get_doc for a whole document.
get_docOne agent doc as markdown: getting-started, authentication, mcp or pricing (pricing includes the live model table).
list_modelsEnabled Splice models with their standard price in credits (100 credits = $1 on the Starter pack). unit "per_generation" = base credits each; "per_second" = credits per second of output (video); "usage" = billed on tokens. variants give…
get_pricingCredit packs (fixed prices), sign-up credits, payment methods and what a credit is. For per-model prices use list_models.
list_templatesBrowse the public template library: curated model + prompt + settings recipes for images, video, music and motion. Returns summaries; get_template returns one with its ready-to-run payload.
get_templateOne public template by slug or id, with its generation payload (model, prompt, settings). Run it with the product server's generate tools, or open its url in Splice.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"splice-docs": {
"type": "http",
"url": "https://splice.film.fun/api/mcp/docs"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http film https://splice.film.fun/api/mcp/docsclaude.ai, ChatGPT and other clients: add https://splice.film.fun/api/mcp/docs as a custom connector in the settings.
- fun.film.splice/spliceanswers, requires sign-inverified in the MCP registry
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.