
SocialSwarm MCP server
Which MCP servers are SocialSwarm's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-27
- Registry namesi.socialswarm/directoryverified in the MCP registry
The registry name sits under socialswarm.si. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-27
- Tools4
- Server calls itselfsocialswarm
- Server version0.1.0
- Protocol version2025-06-18
On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 84 ms.
- Whether its tools do the product's job has not been judged yet.
Once connected
- For "search public GitHub projects by objective or capability", the likely first call is search_swarms.
- update_swarm change data without a sign-in: anyone with the address can call them.
- Parameters are untyped or undescribed in 4 of 4 tools: check arguments before calling.
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 score76 of 100answers 100 · definitions 83 · context 100 · connects 100 · lowered by the warning signs below
- Answered100% of days9 of 9 daily checks
- Median first answer360 ms
- Space in an agent's context≈ 1,194 tokensthe definitions of all its tools (4), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 4 of 4
What an agent can do with it
- can do · search public GitHub projects by objective or capability
- not sure · connect an AI agent to project listings through MCP
- not sure · pick a small starter task in an open project
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
- Tools that change data, on a server that answers without a sign-in: update_swarm
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 (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). 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_swarmsSearch published directory listings by keyword, topic, capability, and self-reported availability. Optional sorting by cached GitHub stars, forks, contributor accounts, latest push, listing dates, or name. GitHub tasks are not synchronized.
get_swarmRead a published listing by ID, slug, or GitHub repository URL. Not found does not create or endorse a project.
register_swarmRegister a public repository your user is authorized to represent. Creates a directory listing only. Use a stable request_id for retries. Publication is explicitly selected.
update_swarmReplace your account's listing using its exact expected_revision. Does not change GitHub. Retries must reuse the same request_id and payload. Draft or archived listings become hidden.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"directory": {
"type": "http",
"url": "https://socialswarm.si/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http socialswarm https://socialswarm.si/mcpclaude.ai, ChatGPT and other clients: add https://socialswarm.si/mcp as a custom connector in the settings.
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.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.