Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "echo-mem": {
      "type": "http",
      "url": "https://api.echo-mem.com/mcp",
      "headers": {
        "Authorization": "Bearer ${ECHO_MEM_TOKEN}"
      }
    }
  }
}

claude mcp add --transport http echo-mem https://api.echo-mem.com/mcp --header "Authorization: Bearer ${ECHO_MEM_TOKEN}"

[mcp_servers.echo-mem]
url = "https://api.echo-mem.com/mcp"
bearer_token_env_var = "ECHO_MEM_TOKEN"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "echo-mem": {
      "type": "remote",
      "url": "https://api.echo-mem.com/mcp",
      "enabled": true,
      "headers": {
        "Authorization": "Bearer {env:ECHO_MEM_TOKEN}"
      }
    }
  }
}

{
  "mcpServers": {
    "echo-mem": {
      "type": "http",
      "url": "https://api.echo-mem.com/mcp",
      "headers": {
        "Authorization": "Bearer ${ECHO_MEM_TOKEN}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=echo-mem&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYXBpLmVjaG8tbWVtLmNvbS9tY3AiLCJoZWFkZXJzIjp7IkF1dGhvcml6YXRpb24iOiJCZWFyZXIgJHtFQ0hPX01FTV9UT0tFTn0ifX0%3D"
}

{
  "servers": {
    "echo-mem": {
      "type": "http",
      "url": "https://api.echo-mem.com/mcp",
      "headers": {
        "Authorization": "Bearer ${ECHO_MEM_TOKEN}"
      }
    }
  }
}

{
  "mcpServers": {
    "echo-mem": {
      "httpUrl": "https://api.echo-mem.com/mcp",
      "headers": {
        "Authorization": "Bearer ${ECHO_MEM_TOKEN}"
      }
    }
  }
}

extensions:
  "echo-mem":
    enabled: true
    name: "echo-mem"
    type: streamable_http
    uri: "https://api.echo-mem.com/mcp"
    headers:
      "Authorization": "Bearer ${ECHO_MEM_TOKEN}"
    timeout: 300

Placeholders to fill from your own secret store: ${ECHO_MEM_TOKEN}. The registry never accepts secret values.

Quality – / 100not scored

Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.

protocoln/a · weight 25

n/a
protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygienen/a · weight 30

n/a
tools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dumptool list unknown (behind auth, not probed, or empty)

stabilityn/a · weight 15

n/a
stability.changes, stability.rug_pulltool list unknown

dependencies67 · weight 15

fail
deps.known_vulns4 advisories to act on (malicious, or rated high or critical with a fix available): GHSA-jhr6-gm9c-rqjv in [email protected] (direct, fixed in 5.6.0), GHSA-29pf-2h5f-8g72 in [email protected] (indirect, fixed in 5.3.0), GHSA-fgcw-684q-jj6r in [email protected] (indirect, fixed in 5.5.0), ...; 3 more of lower severity or without a fix
pass
deps.mcp_sdk_versionmcp 2.2.0, no known advisory
pass
deps.resolvable[email protected] resolved: 86 packages

Tool list unknown · checked 2026-10-19 14:42 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 93 / 100

provenance75

liveness100

freshness100

hygiene100

+repository +website +reachable +uptime-100% +updated-23d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Dependencies

[email protected] PyPI85 dependencies, resolved · MCP SDK mcp 2.2.0 · advisories checked 2026-10-19

advisory	severity	package	fixed in
GHSA-jhr6-gm9c-rqjvsentence-transformers local model loading bypasses trust_remote_code and executes custom Python	critical	`[email protected]`direct	fixed in `5.6.0`
GHSA-29pf-2h5f-8g72HuggingFace transformers vulnerable to remote code execution	high	`[email protected]`indirect	fixed in `5.3.0`
GHSA-fgcw-684q-jj6rhuggingface/transformers: Arbitrary Code Execution During Model Initialization in the LightGlue Model Loading Path	high	`[email protected]`indirect	fixed in `5.5.0`
GHSA-xrqw-3rrv-vx5wTransformers save_pretrained path traversal allows arbitrary file writes through chat template names	high	`[email protected]`indirect	fixed in `5.10.0`
GHSA-x9r9-c232-4q39Hugging Face Transformers downloads custom generation code before trust consent	high	`[email protected]`indirect	no fix yet
GHSA-69w3-r845-3855HuggingFace Transformers allows for arbitrary code execution in the `Trainer` class	moderate	`[email protected]`indirect	fixed in `5.0.0rc3`
PYSEC-2025-217Hugging Face Transformers X-CLIP Checkpoint Conversion Deserialization of Untrusted Data Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Hugging Face Transformers. User interaction is required to exploit this vuln	unrated	`[email protected]`indirect	no fix yet

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://api.echo-mem.com/mcp` streamable-http	api_key `${ECHO_MEM_TOKEN}`	yes	100%	805 ms	–	2026-10-19

package	registry	version	runtime	secrets
`echo-mem`	pypi	0.5.3	–	`ECHO_MEMORY_DATABASE_URL`

Tools (0)

No tools observed. Tools appear once a credential-free probe can list them.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "io.github.ayushcodes10/echo-mem",
  "title": "Echo Memory",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://api.echo-mem.com/mcp",
      "type": "streamable-http",
      "headers": [
        {
          "name": "Authorization",
          "isSecret": true,
          "isRequired": true,
          "description": "Bearer <key>, from https://app.echo-mem.com — the hosted option, which needs no local database."
        }
      ]
    }
  ],
  "version": "0.5.3",
  "packages": [
    {
      "version": "0.5.3",
      "transport": {
        "type": "stdio"
      },
      "identifier": "echo-mem",
      "registryType": "pypi",
      "environmentVariables": [
        {
          "name": "ECHO_MEMORY_DATABASE_URL",
          "isSecret": true,
          "isRequired": true,
          "description": "Postgres connection string. `echo-memory quickstart` starts a suitable database and prints this."
        },
        {
          "name": "ECHO_MEMORY_USER_ID",
          "isRequired": true,
          "description": "Whose memory this is. Scopes every read and write."
        },
        {
          "name": "ECHO_MEMORY_AGENT_ID",
          "isRequired": true,
          "description": "Which tool is writing: claude-code, cursor, codex, claude-desktop. Recorded on every fact, and what makes a cross-tool recall visible afterwards."
        }
      ]
    }
  ],
  "repository": {
    "url": "https://github.com/echo-mem/echo-mem",
    "source": "github"
  },
  "websiteUrl": "https://echo-mem.com",
  "description": "Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM."
}